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

can DTR support YOLOv5? #11

Open
chaoyanghe opened this issue Sep 11, 2022 · 1 comment
Open

can DTR support YOLOv5? #11

chaoyanghe opened this issue Sep 11, 2022 · 1 comment

Comments

@chaoyanghe
Copy link

I want to try this method in memory contrained edge devices for YOLOv5 (https://github.com/ultralytics/yolov5), could you please help to have an example for it? thanks.
@MarisaKirisame
Copy link
Collaborator

Yes it can. I will write a more in-detail dtr-usage doc later (is on a deadline this week), but basically you have to build dtr yourself, then call .checkpoint() for the input tensor, and .apply_.(lambda x: x.detach().checkpoint()) for the model. then you are good

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@MarisaKirisame @chaoyanghe