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.

Sign up for GitHub

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

Jump to bottom

YOLOv7 cuDLA #39

Open
valeriob opened this issue Jun 19, 2024 · 2 comments
Open

YOLOv7 cuDLA #39

valeriob opened this issue Jun 19, 2024 · 2 comments
Assignees
@lynettez
Labels
question Further information is requested triaged

Comments

@valeriob
Copy link

Hi,
is it possible to apply the same method to YOLOv7 ?
@lynettez
Copy link
Collaborator

lynettez commented Sep 2, 2024

If you are referring to running the backbone on DLA and the head on GPU, then the answer is yes. If you mean the QAT part, I'll let @liuanqi-libra7 comment on that.

@lynettez lynettez self-assigned this Sep 2, 2024
@lynettez lynettez added question Further information is requested triaged labels Sep 2, 2024
@liuanqi-libra7
Copy link
Collaborator

I think it is possible, but this requires adjusting the QAT module.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@lynettez lynettez

Labels
question Further information is requested triaged
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@valeriob @lynettez @liuanqi-libra7