add new model

configs/body/2d_kpt_sview_rgb_img/dekr/crowdpose/hrnet_w32_crowdpose_512x512_multiscale.py

+_base_ = ['hrnet_w32_crowdpose_512x512.py']
+
+model = dict(
+    test_cfg=dict(
+        multi_scale_score_decrease=0.9,
+        nms_dist_thr=0.1,
+    ))
+
+val_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='BottomUpGetImgSize',
+        base_length=32,
+        test_scale_factor=[0.5, 1, 2]),
+    dict(
+        type='BottomUpResizeAlign',
+        base_length=32,
+        transforms=[
+            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', 'aug_data', 'test_scale_factor', 'base_size',
+            'center', 'scale', 'flip_index', 'num_joints', 'skeleton',
+            'image_size', 'heatmap_size'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data = dict(
+    val=dict(pipeline=val_pipeline),
+    test=dict(pipeline=test_pipeline),
+)

configs/body/2d_kpt_sview_rgb_img/dekr/crowdpose/hrnet_w48_crowdpose_640x640.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/crowdpose.py'
+]
+checkpoint_config = dict(interval=20)
+evaluation = dict(interval=20, metric='mAP', save_best='AP')
+
+optimizer = dict(
+    type='Adam',
+    lr=0.001,
+)
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=0.001,
+    step=[200, 260])
+total_epochs = 300
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+data_cfg = dict(
+    image_size=640,
+    base_size=320,
+    base_sigma=2,
+    heatmap_size=[160],
+    num_joints=channel_cfg['dataset_joints'],
+    dataset_channel=channel_cfg['dataset_channel'],
+    inference_channel=channel_cfg['inference_channel'],
+    num_scales=1,
+    scale_aware_sigma=False,
+)
+
+# model settings
+model = dict(
+    type='DisentangledKeypointRegressor',
+    pretrained='https://download.openmmlab.com/mmpose/'
+    'pretrain_models/hrnet_w48-8ef0771d.pth',
+    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=(48, 96)),
+            stage3=dict(
+                num_modules=4,
+                num_branches=3,
+                block='BASIC',
+                num_blocks=(4, 4, 4),
+                num_channels=(48, 96, 192)),
+            stage4=dict(
+                num_modules=3,
+                num_branches=4,
+                block='BASIC',
+                num_blocks=(4, 4, 4, 4),
+                num_channels=(48, 96, 192, 384),
+                multiscale_output=True)),
+    ),
+    keypoint_head=dict(
+        type='DEKRHead',
+        in_channels=(48, 96, 192, 384),
+        in_index=(0, 1, 2, 3),
+        num_heatmap_filters=48,
+        num_joints=channel_cfg['dataset_joints'],
+        input_transform='resize_concat',
+        heatmap_loss=dict(
+            type='JointsMSELoss',
+            use_target_weight=True,
+            loss_weight=1.0,
+        ),
+        offset_loss=dict(
+            type='SoftWeightSmoothL1Loss',
+            use_target_weight=True,
+            supervise_empty=False,
+            loss_weight=0.004,
+            beta=1 / 9.0,
+        )),
+    train_cfg=dict(),
+    test_cfg=dict(
+        num_joints=channel_cfg['dataset_joints'],
+        max_num_people=30,
+        project2image=False,
+        align_corners=False,
+        max_pool_kernel=5,
+        use_nms=True,
+        nms_dist_thr=0.05,
+        nms_joints_thr=8,
+        keypoint_threshold=0.01,
+        rescore_cfg=dict(
+            in_channels=59,
+            norm_indexes=(0, 1),
+            pretrained='https://download.openmmlab.com/mmpose/'
+            'pretrain_models/kpt_rescore_crowdpose-300c7efe.pth'),
+        flip_test=True))
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='BottomUpRandomAffine',
+        rot_factor=30,
+        scale_factor=[0.75, 1.5],
+        scale_type='short',
+        trans_factor=40),
+    dict(type='BottomUpRandomFlip', flip_prob=0.5),
+    dict(type='ToTensor'),
+    dict(
+        type='NormalizeTensor',
+        mean=[0.485, 0.456, 0.406],
+        std=[0.229, 0.224, 0.225]),
+    dict(type='GetKeypointCenterArea'),
+    dict(
+        type='BottomUpGenerateHeatmapTarget',
+        sigma=(2, 4),
+        gen_center_heatmap=True,
+        bg_weight=0.1,
+    ),
+    dict(
+        type='BottomUpGenerateOffsetTarget',
+        radius=4,
+    ),
+    dict(
+        type='Collect',
+        keys=['img', 'heatmaps', 'masks', 'offsets', 'offset_weights'],
+        meta_keys=[]),
+]
+
+val_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='BottomUpGetImgSize', test_scale_factor=[1]),
+    dict(
+        type='BottomUpResizeAlign',
+        transforms=[
+            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', 'aug_data', 'test_scale_factor', 'base_size',
+            'center', 'scale', 'flip_index', 'num_joints', 'skeleton',
+            'image_size', 'heatmap_size'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/crowdpose'
+data = dict(
+    workers_per_gpu=4,
+    train_dataloader=dict(samples_per_gpu=5),
+    val_dataloader=dict(samples_per_gpu=1),
+    test_dataloader=dict(samples_per_gpu=1),
+    train=dict(
+        type='BottomUpCrowdPoseDataset',
+        ann_file=f'{data_root}/annotations/mmpose_crowdpose_trainval.json',
+        img_prefix=f'{data_root}/images/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='BottomUpCrowdPoseDataset',
+        ann_file=f'{data_root}/annotations/mmpose_crowdpose_test.json',
+        img_prefix=f'{data_root}/images/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='BottomUpCrowdPoseDataset',
+        ann_file=f'{data_root}/annotations/mmpose_crowdpose_test.json',
+        img_prefix=f'{data_root}/images/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+)

configs/body/2d_kpt_sview_rgb_img/dekr/crowdpose/hrnet_w48_crowdpose_640x640_multiscale.py

+_base_ = ['hrnet_w48_crowdpose_640x640.py']
+
+model = dict(
+    test_cfg=dict(
+        multi_scale_score_decrease=0.9,
+        nms_dist_thr=0.1,
+    ))
+
+val_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='BottomUpGetImgSize',
+        base_length=32,
+        test_scale_factor=[0.5, 1, 2]),
+    dict(
+        type='BottomUpResizeAlign',
+        base_length=32,
+        transforms=[
+            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', 'aug_data', 'test_scale_factor', 'base_size',
+            'center', 'scale', 'flip_index', 'num_joints', 'skeleton',
+            'image_size', 'heatmap_size'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data = dict(
+    val=dict(pipeline=val_pipeline),
+    test=dict(pipeline=test_pipeline),
+)

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/README.md

+# Top-down heatmap-based pose estimation
+
+Top-down methods divide the task into two stages: human detection and pose estimation.
+
+They perform human detection first, followed by single-person pose estimation given human bounding boxes.
+Instead of estimating keypoint coordinates directly, the pose estimator will produce heatmaps which represent the
+likelihood of being a keypoint.
+
+Various neural network models have been proposed for better performance.
+The popular ones include stacked hourglass networks, and HRNet.

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/hrnet_aic.md

+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2019/html/Sun_Deep_High-Resolution_Representation_Learning_for_Human_Pose_Estimation_CVPR_2019_paper.html">HRNet (CVPR'2019)</a></summary>
+
+```bibtex
+@inproceedings{sun2019deep,
+  title={Deep high-resolution representation learning for human pose estimation},
+  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={5693--5703},
+  year={2019}
+}
+```
+
+</details>
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/1711.06475">AI Challenger (ArXiv'2017)</a></summary>
+
+```bibtex
+@article{wu2017ai,
+  title={Ai challenger: A large-scale dataset for going deeper in image understanding},
+  author={Wu, Jiahong and Zheng, He and Zhao, Bo and Li, Yixin and Yan, Baoming and Liang, Rui and Wang, Wenjia and Zhou, Shipei and Lin, Guosen and Fu, Yanwei and others},
+  journal={arXiv preprint arXiv:1711.06475},
+  year={2017}
+}
+```
+
+</details>
+
+Results on AIC val set with ground-truth bounding boxes
+
+| Arch                                          | Input Size |  AP   | AP<sup>50</sup> | AP<sup>75</sup> |  AR   | AR<sup>50</sup> |                     ckpt                      |                      log                      |
+| :-------------------------------------------- | :--------: | :---: | :-------------: | :-------------: | :---: | :-------------: | :-------------------------------------------: | :-------------------------------------------: |
+| [pose_hrnet_w32](/configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/hrnet_w32_aic_256x192.py) |  256x192   | 0.323 |      0.762      |      0.219      | 0.366 |      0.789      | [ckpt](https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w32_aic_256x192-30a4e465_20200826.pth) | [log](https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w32_aic_256x192_20200826.log.json) |

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/hrnet_aic.yml

+Collections:
+- Name: HRNet
+  Paper:
+    Title: Deep high-resolution representation learning for human pose estimation
+    URL: http://openaccess.thecvf.com/content_CVPR_2019/html/Sun_Deep_High-Resolution_Representation_Learning_for_Human_Pose_Estimation_CVPR_2019_paper.html
+  README: https://github.com/open-mmlab/mmpose/blob/master/docs/en/papers/backbones/hrnet.md
+Models:
+- Config: configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/hrnet_w32_aic_256x192.py
+  In Collection: HRNet
+  Metadata:
+    Architecture:
+    - HRNet
+    Training Data: AI Challenger
+  Name: topdown_heatmap_hrnet_w32_aic_256x192
+  Results:
+  - Dataset: AI Challenger
+    Metrics:
+      AP: 0.323
+      AP@0.5: 0.762
+      AP@0.75: 0.219
+      AR: 0.366
+      AR@0.5: 0.789
+    Task: Body 2D Keypoint
+  Weights: https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w32_aic_256x192-30a4e465_20200826.pth

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/hrnet_w32_aic_256x192.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/aic.py'
+]
+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
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+# model settings
+model = dict(
+    type='TopDown',
+    pretrained='https://download.openmmlab.com/mmpose/'
+    'pretrain_models/hrnet_w32-36af842e.pth',
+    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='TopdownHeatmapSimpleHead',
+        in_channels=32,
+        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_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=True,
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='Collect',
+        keys=['img'],
+        meta_keys=[
+            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
+            'flip_pairs'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/aic'
+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='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_train.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_train_20170902/'
+        'keypoint_train_images_20170902/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}))

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/hrnet_w32_aic_384x288.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/aic.py'
+]
+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
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+# model settings
+model = dict(
+    type='TopDown',
+    pretrained='https://download.openmmlab.com/mmpose/'
+    'pretrain_models/hrnet_w32-36af842e.pth',
+    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='TopdownHeatmapSimpleHead',
+        in_channels=32,
+        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_cfg = dict(
+    image_size=[288, 384],
+    heatmap_size=[72, 96],
+    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=True,
+    det_bbox_thr=0.0,
+    bbox_file='data/person_detection_results/'
+    'COCO_val2017_detections_AP_H_56_person.json',
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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=3),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='Collect',
+        keys=['img'],
+        meta_keys=[
+            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
+            'flip_pairs'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/aic'
+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='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_train.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_train_20170902/'
+        'keypoint_train_images_20170902/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}))

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/hrnet_w48_aic_256x192.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/aic.py'
+]
+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
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+# model settings
+model = dict(
+    type='TopDown',
+    pretrained='https://download.openmmlab.com/mmpose/'
+    'pretrain_models/hrnet_w48-8ef0771d.pth',
+    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=(48, 96)),
+            stage3=dict(
+                num_modules=4,
+                num_branches=3,
+                block='BASIC',
+                num_blocks=(4, 4, 4),
+                num_channels=(48, 96, 192)),
+            stage4=dict(
+                num_modules=3,
+                num_branches=4,
+                block='BASIC',
+                num_blocks=(4, 4, 4, 4),
+                num_channels=(48, 96, 192, 384))),
+    ),
+    keypoint_head=dict(
+        type='TopdownHeatmapSimpleHead',
+        in_channels=48,
+        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_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=True,
+    det_bbox_thr=0.0,
+    bbox_file='data/person_detection_results/'
+    'COCO_val2017_detections_AP_H_56_person.json',
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='Collect',
+        keys=['img'],
+        meta_keys=[
+            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
+            'flip_pairs'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/aic'
+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='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_train.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_train_20170902/'
+        'keypoint_train_images_20170902/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}))

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/hrnet_w48_aic_384x288.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/aic.py'
+]
+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=None,
+    # warmup='linear',
+    # warmup_iters=500,
+    # warmup_ratio=0.001,
+    step=[170, 200])
+total_epochs = 210
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+# model settings
+model = dict(
+    type='TopDown',
+    pretrained='https://download.openmmlab.com/mmpose/'
+    'pretrain_models/hrnet_w48-8ef0771d.pth',
+    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=(48, 96)),
+            stage3=dict(
+                num_modules=4,
+                num_branches=3,
+                block='BASIC',
+                num_blocks=(4, 4, 4),
+                num_channels=(48, 96, 192)),
+            stage4=dict(
+                num_modules=3,
+                num_branches=4,
+                block='BASIC',
+                num_blocks=(4, 4, 4, 4),
+                num_channels=(48, 96, 192, 384))),
+    ),
+    keypoint_head=dict(
+        type='TopdownHeatmapSimpleHead',
+        in_channels=48,
+        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_cfg = dict(
+    image_size=[288, 384],
+    heatmap_size=[72, 96],
+    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=True,
+    det_bbox_thr=0.0,
+    bbox_file='data/person_detection_results/'
+    'COCO_val2017_detections_AP_H_56_person.json',
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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=3),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='Collect',
+        keys=['img'],
+        meta_keys=[
+            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
+            'flip_pairs'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/aic'
+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='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_train.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_train_20170902/'
+        'keypoint_train_images_20170902/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}))

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/res101_aic_256x192.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/aic.py'
+]
+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
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+# model settings
+model = dict(
+    type='TopDown',
+    pretrained='torchvision://resnet101',
+    backbone=dict(type='ResNet', depth=101),
+    keypoint_head=dict(
+        type='TopdownHeatmapSimpleHead',
+        in_channels=2048,
+        out_channels=channel_cfg['num_output_channels'],
+        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=True,
+    det_bbox_thr=0.0,
+    bbox_file='data/person_detection_results/'
+    'COCO_val2017_detections_AP_H_56_person.json',
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='Collect',
+        keys=['img'],
+        meta_keys=[
+            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
+            'flip_pairs'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/aic'
+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='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_train.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_train_20170902/'
+        'keypoint_train_images_20170902/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}))

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/res101_aic_384x288.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/aic.py'
+]
+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
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+# model settings
+model = dict(
+    type='TopDown',
+    pretrained='torchvision://resnet101',
+    backbone=dict(type='ResNet', depth=101),
+    keypoint_head=dict(
+        type='TopdownHeatmapSimpleHead',
+        in_channels=2048,
+        out_channels=channel_cfg['num_output_channels'],
+        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=[288, 384],
+    heatmap_size=[72, 96],
+    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=True,
+    det_bbox_thr=0.0,
+    bbox_file='data/person_detection_results/'
+    'COCO_val2017_detections_AP_H_56_person.json',
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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=3),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='Collect',
+        keys=['img'],
+        meta_keys=[
+            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
+            'flip_pairs'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/aic'
+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='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_train.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_train_20170902/'
+        'keypoint_train_images_20170902/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}))

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/res152_aic_256x192.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/aic.py'
+]
+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
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+# model settings
+model = dict(
+    type='TopDown',
+    pretrained='torchvision://resnet152',
+    backbone=dict(type='ResNet', depth=152),
+    keypoint_head=dict(
+        type='TopdownHeatmapSimpleHead',
+        in_channels=2048,
+        out_channels=channel_cfg['num_output_channels'],
+        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=True,
+    det_bbox_thr=0.0,
+    bbox_file='data/person_detection_results/'
+    'COCO_val2017_detections_AP_H_56_person.json',
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='Collect',
+        keys=['img'],
+        meta_keys=[
+            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
+            'flip_pairs'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/aic'
+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='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_train.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_train_20170902/'
+        'keypoint_train_images_20170902/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}))

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/res152_aic_384x288.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/aic.py'
+]
+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
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+# model settings
+model = dict(
+    type='TopDown',
+    pretrained='torchvision://resnet152',
+    backbone=dict(type='ResNet', depth=152),
+    keypoint_head=dict(
+        type='TopdownHeatmapSimpleHead',
+        in_channels=2048,
+        out_channels=channel_cfg['num_output_channels'],
+        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=[288, 384],
+    heatmap_size=[72, 96],
+    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=True,
+    det_bbox_thr=0.0,
+    bbox_file='data/person_detection_results/'
+    'COCO_val2017_detections_AP_H_56_person.json',
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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=3),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='Collect',
+        keys=['img'],
+        meta_keys=[
+            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
+            'flip_pairs'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/aic'
+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='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_train.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_train_20170902/'
+        'keypoint_train_images_20170902/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}))

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/res50_aic_256x192.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/aic.py'
+]
+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
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+# model settings
+model = dict(
+    type='TopDown',
+    pretrained='torchvision://resnet50',
+    backbone=dict(type='ResNet', depth=50),
+    keypoint_head=dict(
+        type='TopdownHeatmapSimpleHead',
+        in_channels=2048,
+        out_channels=channel_cfg['num_output_channels'],
+        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=True,
+    det_bbox_thr=0.0,
+    bbox_file='',
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='Collect',
+        keys=['img'],
+        meta_keys=[
+            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
+            'flip_pairs'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/aic'
+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='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_train.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_train_20170902/'
+        'keypoint_train_images_20170902/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}))

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/res50_aic_384x288.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/aic.py'
+]
+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
+channel_cfg = dict(
+    num_output_channels=14,
+    dataset_joints=14,
+    dataset_channel=[
+        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],
+    ],
+    inference_channel=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13])
+
+# model settings
+model = dict(
+    type='TopDown',
+    pretrained='torchvision://resnet50',
+    backbone=dict(type='ResNet', depth=50),
+    keypoint_head=dict(
+        type='TopdownHeatmapSimpleHead',
+        in_channels=2048,
+        out_channels=channel_cfg['num_output_channels'],
+        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=[288, 384],
+    heatmap_size=[72, 96],
+    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=True,
+    det_bbox_thr=0.0,
+    bbox_file='data/person_detection_results/'
+    'COCO_val2017_detections_AP_H_56_person.json',
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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=3),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='Collect',
+        keys=['img'],
+        meta_keys=[
+            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
+            'flip_pairs'
+        ]),
+]
+
+test_pipeline = val_pipeline
+
+data_root = 'data/aic'
+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='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_train.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_train_20170902/'
+        'keypoint_train_images_20170902/',
+        data_cfg=data_cfg,
+        pipeline=train_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    val=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=val_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+    test=dict(
+        type='TopDownAicDataset',
+        ann_file=f'{data_root}/annotations/aic_val.json',
+        img_prefix=f'{data_root}/ai_challenger_keypoint_validation_20170911/'
+        'keypoint_validation_images_20170911/',
+        data_cfg=data_cfg,
+        pipeline=test_pipeline,
+        dataset_info={{_base_.dataset_info}}))

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/resnet_aic.md

+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_ECCV_2018/html/Bin_Xiao_Simple_Baselines_for_ECCV_2018_paper.html">SimpleBaseline2D (ECCV'2018)</a></summary>
+
+```bibtex
+@inproceedings{xiao2018simple,
+  title={Simple baselines for human pose estimation and tracking},
+  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
+  booktitle={Proceedings of the European conference on computer vision (ECCV)},
+  pages={466--481},
+  year={2018}
+}
+```
+
+</details>
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html">ResNet (CVPR'2016)</a></summary>
+
+```bibtex
+@inproceedings{he2016deep,
+  title={Deep residual learning for image recognition},
+  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={770--778},
+  year={2016}
+}
+```
+
+</details>
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/1711.06475">AI Challenger (ArXiv'2017)</a></summary>
+
+```bibtex
+@article{wu2017ai,
+  title={Ai challenger: A large-scale dataset for going deeper in image understanding},
+  author={Wu, Jiahong and Zheng, He and Zhao, Bo and Li, Yixin and Yan, Baoming and Liang, Rui and Wang, Wenjia and Zhou, Shipei and Lin, Guosen and Fu, Yanwei and others},
+  journal={arXiv preprint arXiv:1711.06475},
+  year={2017}
+}
+```
+
+</details>
+
+Results on AIC val set with ground-truth bounding boxes
+
+| Arch                                          | Input Size |  AP   | AP<sup>50</sup> | AP<sup>75</sup> |  AR   | AR<sup>50</sup> |                     ckpt                      |                      log                      |
+| :-------------------------------------------- | :--------: | :---: | :-------------: | :-------------: | :---: | :-------------: | :-------------------------------------------: | :-------------------------------------------: |
+| [pose_resnet_101](/configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/res101_aic_256x192.py) |  256x192   | 0.294 |      0.736      |      0.174      | 0.337 |      0.763      | [ckpt](https://download.openmmlab.com/mmpose/top_down/resnet/res101_aic_256x192-79b35445_20200826.pth) | [log](https://download.openmmlab.com/mmpose/top_down/resnet/res101_aic_256x192_20200826.log.json) |

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/resnet_aic.yml

+Collections:
+- Name: SimpleBaseline2D
+  Paper:
+    Title: Simple baselines for human pose estimation and tracking
+    URL: http://openaccess.thecvf.com/content_ECCV_2018/html/Bin_Xiao_Simple_Baselines_for_ECCV_2018_paper.html
+  README: https://github.com/open-mmlab/mmpose/blob/master/docs/en/papers/algorithms/simplebaseline2d.md
+Models:
+- Config: configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/aic/res101_aic_256x192.py
+  In Collection: SimpleBaseline2D
+  Metadata:
+    Architecture:
+    - SimpleBaseline2D
+    - ResNet
+    Training Data: AI Challenger
+  Name: topdown_heatmap_res101_aic_256x192
+  Results:
+  - Dataset: AI Challenger
+    Metrics:
+      AP: 0.294
+      AP@0.5: 0.736
+      AP@0.75: 0.174
+      AR: 0.337
+      AR@0.5: 0.763
+    Task: Body 2D Keypoint
+  Weights: https://download.openmmlab.com/mmpose/top_down/resnet/res101_aic_256x192-79b35445_20200826.pth

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/2xmspn50_coco_256x192.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/coco.py'
+]
+evaluation = dict(interval=10, metric='mAP', save_best='AP')
+
+optimizer = dict(
+    type='Adam',
+    lr=5e-3,
+)
+
+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
+model = dict(
+    type='TopDown',
+    pretrained='torchvision://resnet50',
+    backbone=dict(
+        type='MSPN',
+        unit_channels=256,
+        num_stages=2,
+        num_units=4,
+        num_blocks=[3, 4, 6, 3],
+        norm_cfg=dict(type='BN')),
+    keypoint_head=dict(
+        type='TopdownHeatmapMSMUHead',
+        out_shape=(64, 48),
+        unit_channels=256,
+        out_channels=channel_cfg['num_output_channels'],
+        num_stages=2,
+        num_units=4,
+        use_prm=False,
+        norm_cfg=dict(type='BN'),
+        loss_keypoint=([
+            dict(
+                type='JointsMSELoss', use_target_weight=True, loss_weight=0.25)
+        ] * 3 + [
+            dict(
+                type='JointsOHKMMSELoss',
+                use_target_weight=True,
+                loss_weight=1.)
+        ]) * 2),
+    train_cfg=dict(),
+    test_cfg=dict(
+        flip_test=True,
+        post_process='megvii',
+        shift_heatmap=False,
+        modulate_kernel=5))
+
+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,
+    use_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='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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',
+        kernel=[(15, 15), (11, 11), (9, 9), (7, 7)] + [(11, 11), (9, 9),
+                                                       (7, 7), (5, 5)],
+        encoding='Megvii'),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='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=32,
+    workers_per_gpu=4,
+    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,
+        dataset_info={{_base_.dataset_info}}),
+    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,
+        dataset_info={{_base_.dataset_info}}),
+    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=test_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+)

configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/2xrsn50_coco_256x192.py

+_base_ = [
+    '../../../../_base_/default_runtime.py',
+    '../../../../_base_/datasets/coco.py'
+]
+evaluation = dict(interval=10, metric='mAP', save_best='AP')
+
+optimizer = dict(
+    type='Adam',
+    lr=5e-3,
+)
+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
+model = dict(
+    type='TopDown',
+    pretrained=None,
+    backbone=dict(
+        type='RSN',
+        unit_channels=256,
+        num_stages=2,
+        num_units=4,
+        num_blocks=[3, 4, 6, 3],
+        num_steps=4,
+        norm_cfg=dict(type='BN')),
+    keypoint_head=dict(
+        type='TopdownHeatmapMSMUHead',
+        out_shape=(64, 48),
+        unit_channels=256,
+        out_channels=channel_cfg['num_output_channels'],
+        num_stages=2,
+        num_units=4,
+        use_prm=False,
+        norm_cfg=dict(type='BN'),
+        loss_keypoint=([
+            dict(
+                type='JointsMSELoss', use_target_weight=True, loss_weight=0.25)
+        ] * 3 + [
+            dict(
+                type='JointsOHKMMSELoss',
+                use_target_weight=True,
+                loss_weight=1.)
+        ]) * 2),
+    train_cfg=dict(),
+    test_cfg=dict(
+        flip_test=True,
+        post_process='megvii',
+        shift_heatmap=False,
+        modulate_kernel=5))
+
+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,
+    use_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='TopDownGetBboxCenterScale', padding=1.25),
+    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
+    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',
+        kernel=[(15, 15), (11, 11), (9, 9), (7, 7)] + [(11, 11), (9, 9),
+                                                       (7, 7), (5, 5)],
+        encoding='Megvii'),
+    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='TopDownGetBboxCenterScale', padding=1.25),
+    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='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=32,
+    workers_per_gpu=4,
+    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,
+        dataset_info={{_base_.dataset_info}}),
+    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,
+        dataset_info={{_base_.dataset_info}}),
+    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=test_pipeline,
+        dataset_info={{_base_.dataset_info}}),
+)