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

How to specify GPU id in nuclio functions? #6104

Open
yuanyuangoo opened this issue May 4, 2023 · 8 comments
Open

How to specify GPU id in nuclio functions? #6104

yuanyuangoo opened this issue May 4, 2023 · 8 comments
Labels
enhancement New feature or request

Comments

@yuanyuangoo
Copy link

I am using sam to help the labelling, which use a GPU. What should I do to specify a certain GPU to use?

@315386775
Copy link

Good job. with sam model the cvat may get more stars and attention.

@bsekachev
Copy link
Member

Probably it can be configured via configuration .yml file.

@bsekachev bsekachev added the enhancement New feature or request label May 9, 2023
@315386775
Copy link

@bsekachev are there any plans to integrate SAM into CVAT.

@yuanyuangoo
Copy link
Author

@bsekachev are there any plans to integrate SAM into CVAT.

I am using it.

@bsekachev
Copy link
Member

@bsekachev bsekachev changed the title How to specify gpu id for serverless SAM fuction? How to specify GPU id in nuclio functions? May 11, 2023
@yuanyuangoo
Copy link
Author

yuanyuangoo commented May 16, 2023 via email

@twmht
Copy link

twmht commented May 31, 2023

@bsekachev

Can we integrate our own model with cvat? and of tutorial?

@silverlining21
Copy link

Change the follow line into
https://github.com/opencv/cvat/blob/f52f0f3e0ea09b72bc3efdead9780ca2fb2a858c/serverless/pytorch/facebookresearch/sam/nuclio/function-gpu.yaml#L36

value: NVIDIA_VISIBLE_DEVICES=2

Make sure you specify your GPU id during image building. Make sure your env works well for the gpu, such as nv driver nv-docker all sounds work well.
enjoy!

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