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

add/ViT #10

Open
OliverZim opened this issue Jun 3, 2023 · 1 comment
Open

add/ViT #10

OliverZim opened this issue Jun 3, 2023 · 1 comment

Comments

@OliverZim
Copy link
Collaborator

  • add the standard Visual Transformer model to the codebase
  • we might be able to use the version already provided by monai
  • afterwards we should experiment with the architecture and make some changes
@OliverZim
Copy link
Collaborator Author

I added the ViT model from monai and made some minor changes to allow for classification. But with the current architecture I always get a torch.cuda.OutOfMemoryError: CUDA out of memory error. Reducing the batch size to 1 did not help and also distributed training across two GPUs (2008 Ti) did not resolve the error.

This needs further investigation. #18

Experiments have therefor not yet been conducted.

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
1 participant
@OliverZim