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

Can this model fine-tuning with coco dataset? #13

Open
skyfallsss opened this issue Jan 19, 2024 · 5 comments
Open

Can this model fine-tuning with coco dataset? #13

skyfallsss opened this issue Jan 19, 2024 · 5 comments

Comments

@skyfallsss
Copy link

The medical dataset I use is coco fornat.I cannot find the guidance on it.

@ngctnnnn
Copy link
Collaborator

Hi,

Can you demonstrate your problem more detailedly ?

@skyfallsss
Copy link
Author

I want to know the format of the dataset llvm-med use. My dataset's format is the coco format of object instances. Can I use my dataset without converting to finetune llvm-med model?

@skyfallsss
Copy link
Author

  1. Prompt-based Segmentation with ViT-B
    a. Prompt-based segmentation with fine-tuned decoder of SAM (MedSAM).
    about this method training ,what is the dataset format? coco format or others.

@ngctnnnn
Copy link
Collaborator

On the prompt-based segmentation, bounding boxes that serve as the prompt are in the format of x_min, y_min, x_max, y_max.

Hope it might help.

@ngctnnnn
Copy link
Collaborator

You could discover more or adjust for your best suit by observing the dataloader/dataset.py file.

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