Skip to content
New issue

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

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

Already on GitHub? Sign in to your account

Integration of state of the art pose estimation: ViTPose. #1389

Open
khanhha opened this issue May 24, 2022 · 3 comments
Open

Integration of state of the art pose estimation: ViTPose. #1389

khanhha opened this issue May 24, 2022 · 3 comments
Labels
enhancement New feature or request

Comments

@khanhha
Copy link

khanhha commented May 24, 2022

Hi awesome developers from MMPose.
A new state of the art pose estimation research has published their code. https://github.com/ViTAE-Transformer/ViTPose
MMPose is the leading open-source project in this field, so I am really looking forward for an integration of this research into MMPose.
Thanks

@liqikai9
Copy link
Collaborator

Thanks for your interest in MMPose and your suggestion. We will look into it. You can also comment on the roadmap of MMPose here.

@jin-s13 jin-s13 added the enhancement New feature or request label May 25, 2022
@Annbless
Copy link
Contributor

Annbless commented May 26, 2022

Hi@khanhha, Thanks for your interest in ViTPose.

Hi, awesome developers from MMPose. Thanks for your fantastic work in MMPose. The framework is wonderful and helps greatly in our ViTPose and other pose works!

We are willing to integrate ViTPose into MMPose and contribute to the community. Most of the modifications exist in the backbone folder (i.e., register a new backbone) and the head (i.e., support a simpler decoder and add a parameter for control) file. A new optimizer constructor is also utilized in the mmcv_custom folder to support layer-wise learning rate decay for training.

If there is anything that we could help with, please do not hesitate to contact us.

@ly015
Copy link
Member

ly015 commented May 26, 2022

@Annbless Thank you very much for your help! It's inspiring to see that MMPose is facilitating great research works like ViTPose and bringing convenience to the community. And the contribution from the community is very much appreciated. We are looking forward to your PRs to integrate ViTPose into MMPose. Please let us know if there is anything we can help with.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

5 participants