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

Update on the binary image segmentation example #594

Open
wants to merge 1 commit into
base: master
Choose a base branch
from

Conversation

omidvarnia
Copy link

No description provided.

@omidvarnia
Copy link
Author

Hi @qubvel,

I attempted to run your notebook example for binary segmentation on our cluster, which has a low-memory GPU. However, the pytorch_lightning trainer encountered issues in this environment, so I had to refactor the training process using a conventional torch training loop.

I tested the modified script (binary_segmentation_intro.py) on a single CPU with a limited run of 10 epochs. While the training process was considerably slow, the implementation appears to be functioning correctly.

I wanted to share this feedback with you and express my appreciation for your valuable contributions to the field.

Regards;
Amir

@qubvel
Copy link
Owner

qubvel commented Feb 10, 2025

Hey @omidvarnia , thanks for contribution! I think you opened a PR for a wrong repo, it's a keras repo, can you please reopen against pytorch one? Thanks

@omidvarnia
Copy link
Author

Sure, will do it shortly.

@omidvarnia
Copy link
Author

Thanks @qubvel! I will address your comments and get back to you.

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

Successfully merging this pull request may close these issues.

2 participants