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

Feature Request: Restart option for the feature extraction pipeline #893

Open
GeorgeBatch opened this issue Dec 5, 2024 · 1 comment · May be fixed by #578
Open

Feature Request: Restart option for the feature extraction pipeline #893

GeorgeBatch opened this issue Dec 5, 2024 · 1 comment · May be fixed by #578

Comments

@GeorgeBatch
Copy link
Contributor

  • TIA Toolbox version: develop branch
  • Python version: 3.11
  • Operating System: linux

Feature Request

I am computing features from a bunch of Whole Slide Images using code like in https://github.com/TissueImageAnalytics/tiatoolbox/blob/develop/examples/11-import-foundation-models.ipynb

I think a restart option would be very beneficial when computing features for many slides.

Currently, the save directory is checked. If it already exists, the process terminates with an Error. This is good to prevent overwriting, but restarting would be also good to have, if asked for. To implement the restart option, I think the overwriting prevention would need to be handled on slide level instead of checking the existence of a directory, which means that instead of numbered features, real names would probably need to be used when saving features and positions npy files.

@shaneahmed shaneahmed linked a pull request Jan 24, 2025 that will close this issue
@shaneahmed
Copy link
Member

The new engine design #578 allows you to overwrite existing results. We will update the design to skip the WSIs which have been processed already.

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 a pull request may close this issue.

2 participants