-
Notifications
You must be signed in to change notification settings - Fork 9.6k
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
[Feature] Support DETRs with Hybrid Matching #8655
base: dev
Are you sure you want to change the base?
Conversation
@@ -0,0 +1,184 @@ | |||
_base_ = [ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Would you mind making the original two-stage deformable-detr as base then we can notice all modifications which indicate the tricks
Thanks for your great work! |
344d3eb
to
a13c485
Compare
@okotaku Thanks a lot for your help in creating PR for our HDETR! It would be great if you could check our latest repo based on MMdetection: https://github.com/HDETR/H-Deformable-DETR-mmdet/tree/mmdetection-with-plug-in We would really appreciate your efforts if you could help migrate the complete implementations and pre-trained checkpoints! |
@PkuRainBow Thank you for your sharing! It sounds good. I will try it after refactoring of DETRs. |
Motivation
DETRs with Hybrid Matching
official repo
Result
Checklist