feat: implement get_n_patches and get_image_mask methods for ColIdefics3Processor #343
+117
−2
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
|
Awesome, thanks ! |
|
Well, it's definitely not ideal... Here are some maps for the most common examples I've seen ( Which hour of the day had the highest overall electricity generation in 2019?
Quelle partie de la production pétrolière du Kazakhstan provient de champs en mer ?
|
ManuelFay
reviewed
Nov 2, 2025
There was a problem hiding this comment.
From the images, it seems this is not working at all. I suspect the signal is very noisy because of pixel shuffling. In all cases, I believe this should not be merged as is, because it is not functional.
@paultltc do you see if there is somethign wrong here ? do you think this would apply to modernvbert ?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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 both methods for ColIdefics3Processor, making it possible to use interpretability on colsmol models as well. Since these models do not use a fixed number of patches, but it depends on the image resolution,