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

cryoCARE denoising jobs still only use 1 GPU #1232

Open
andreanans opened this issue Jan 27, 2025 · 2 comments
Open

cryoCARE denoising jobs still only use 1 GPU #1232

andreanans opened this issue Jan 27, 2025 · 2 comments

Comments

@andreanans
Copy link

Hi, I'm testing CryoCARE denoising in relion-5.0 stable (5.0.0-commit-d24f65). However it looks like we can still only supply 1 GPU in the command, despite CryoCARE 0.3 being able to parallelise over multiple GPUs. (https://github.com/juglab/cryoCARE_pip)

Can the cryoCARE wrapper please be updated so we can run CryoCARE jobs on multiple GPUs?

Thanks,

Andrea

@andreanans andreanans changed the title cryoCARE denoising job still only use 1 GPU cryoCARE denoising jobs still only use 1 GPU Jan 27, 2025
@DanGonite57
Copy link

You can specify multiple gpus by adding more flags manually in the "Which GPU to use" field or in "Additional arguments", and it seems like it will correctly use all of them to perform training

Eg Which GPU to use: 0 --gpu 1 --gpu 2 --gpu 3

@andreanans
Copy link
Author

Thanks for the tip. This could be useful to a lot of people. Will it be added to the documentation at some point, or will the wrapper be updated?

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

No branches or pull requests

2 participants