Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Sota result or just for fun? #26

Open
2050airobert opened this issue Jun 11, 2022 · 2 comments
Open

Sota result or just for fun? #26

2050airobert opened this issue Jun 11, 2022 · 2 comments

Comments

@2050airobert
Copy link

2050airobert commented Jun 11, 2022

No description provided.

@fire717
Copy link
Owner

fire717 commented Jun 11, 2022

这些问题readme和谷歌博客其实都有答案, 就不能先看看再提问吗?

  1. 原始模型因为有大量非开源内部数据训练(Evaluations on the Active validation dataset show a significant performance boost relative to identical architectures trained using only COCO. ),在没有同样数据训练的情况下,你没办法比较复现的模型效果是否一致
  2. movenet本身追求的是轻量级,是嵌入式设备的实时性,因此精度上肯定比不上sota模型(比如bottom-up的openpose、top-bottom的hrnet),只能说在有足够、高质量的数据下还是能取得不错的精度
  3. In readme part3:Surely this is a muti-task learning. So add some loss to learn together may improve the performence. (Such as BoneLoss which I have added.)

@2050airobert
Copy link
Author

2050airobert commented Jun 13, 2022

test

# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants