Implement User-Defined Feature Extractor Support #17
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
adas2125
reviewed
Jan 20, 2024
| df['id_patient'], df['type'] = zip(*df['file'].apply(extract_tcga_info)) | ||
| else: | ||
| #TODO: This behavior seems dangerous. Shouldn't we have a separated script | ||
| #and describe the input files definition so we don't need to update code |
Collaborator
There was a problem hiding this comment.
Yes I agree, I think we can define id_patient in the dataset class itself.
adas2125
reviewed
Jan 20, 2024
| # (2, 3, 5) | ||
| # Path to the pickle file containing metadata for the .svs files | ||
| # Example: meta/dhmc_rcc_svs.pickle | ||
| # TODO: This is a saving path, right? We should clarify that this is not input. |
Collaborator
There was a problem hiding this comment.
Yes, a meta-file is created by 01_get_svs_meta.py and then is used by other pre-processing scripts such as 02_patch_extraction.py
adas2125
reviewed
Jan 20, 2024
| # (2) | ||
| # Mask magnification for color filtering during patch extraction. | ||
| # A lower magnification will run faster but will be less precise | ||
| #TODO: Ask why this value? |
Collaborator
There was a problem hiding this comment.
I am not sure. Maybe we should give the user a choice to set this value themselves?
adas2125
approved these changes
Jan 20, 2024
Collaborator
adas2125
left a comment
adas2125
left a comment
There was a problem hiding this comment.
The changes look good. I can work on handling some of the TODO comments as well.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR introduces the capability to load custom feature extractors in our model.
Usage: Set the pretrained model path in config.patch.pretrained_model_path. The system handles integration with the base model architecture.