Support STAR Loss 支持 STAR Loss

[OpenMMLab-Assistant-004]

Support STAR Loss

支持 STAR Loss

Support STAR loss in MMPose.

1. Refer to repo](https://github.com/ZhenglinZhou/STAR/blob/master/lib/loss/starLoss_v2.py))
2. Train and test on WFLW dataset to reproduce the accuracy in paper
3. Train models on other datasets

将 CVPR 2023 论文 STAR loss 的实现加入到 MMPose 中，参考 repo](https://github.com/ZhenglinZhou/STAR/blob/master/lib/loss/starLoss_v2.py))

1. 在人脸 WFLW 数据集上测试，进行训练精度对齐
2. 在其他关键点数据集上进行验证

Task Information

Repository：MMPose

Difficulty：Medium

Points：30

Estimated Time Consumption：21 days

Task Status

Claimant's Github ID：None

Claim Time：None

PR Link：None

Points to Note

To claim the task, please reply Claim the mission in the comment section. After claiming the task, please add our assistant bot called MeowMewo on WeChat at: openmmlabwx.

After completing the task, please submit a PR with the title starting with [MMSIG]. After submission, please reply with your PR link in the comments section of this Discussion. We will review your work as soon as possible.

在评论区回复 Claim the mission 领取任务，领取任务后请及时添加小助手喵喵微信: openmmlabwx

完成任务后提交相关链接（如是PR，标题请以[MMSIG]开头）回复到本Disucssion评论区，我们会第一时间审核您的贡献。

[chg0901]

Claim the mission