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

[FEA] DeepZoomGenerator #778

Open
Pidem opened this issue Sep 10, 2024 · 2 comments
Open

[FEA] DeepZoomGenerator #778

Pidem opened this issue Sep 10, 2024 · 2 comments
Assignees
Labels
feature request New feature or request

Comments

@Pidem
Copy link

Pidem commented Sep 10, 2024

Is your feature request related to a problem? Please describe.
I would like to generate tiles for pathology images and need cuCIM to support the openslide.deepzoom.DeepZoomGenerator class

Describe the solution you'd like
support the DeepZoomGenerator that wraps CuImage

Describe alternatives you've considered
Using Open-slide only and not cuCIM

Additional context
Urgent request for Foundational Model training

@Pidem Pidem added the feature request New feature or request label Sep 10, 2024
@gigony
Copy link
Contributor

gigony commented Sep 14, 2024

Hi @Pidem ,

Thank you for the feature request!
Would you mind sharing more details about your use case?
Do you require the exact same API as OpenSlide's DeepZoomGenerator API (link) for visualization as well, or do you primarily need to generate tiles at a specific zoom level (for levels not supported by the underlying TIFF's tile levels), tile size, or overlap specifically for training purposes?

I'm also curious to know which part of the existing API makes it difficult to adapt to your needs.

Please also let us know if using tiffslide (based on tifffile) would suit your use case. We'd love to hear more about your specific requirements (e.g., performance, usability) for your use cases.

Thanks!

@gigony gigony self-assigned this Sep 14, 2024
@Pidem
Copy link
Author

Pidem commented Oct 8, 2024

I am generating the tiles at a specific zoom level and generating an embedding representation of a given slide using a vision foundational model. I am not exactly sure how tiffslide and cucim differ from each other

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

No branches or pull requests

2 participants