Generalize MMImageMaskInput to ImageMaskInput #1677
Closed
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
Summary: as title, as there is only one color used to mask out Reviewed By: Ayush-Warikoo Differential Revision: D87944294
Summary: following the discussion in D87818563, `MMImageMaskInput` can be generalized for non-LLM image model. So we rename the class as `ImageMaskInput` and make the `processor_fn` as optional. By default, if `processor_fn` is not given, the model input will be the (ablated) image Reviewed By: craymichael Differential Revision: D87946132
Contributor
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Dec 1, 2025
Summary: following the discussion in D87818563, `MMImageMaskInput` can be generalized for non-LLM image model. So we rename the class as `ImageMaskInput` and make the `processor_fn` as optional. By default, if `processor_fn` is not given, the model input will be the (ablated) image Reviewed By: craymichael Differential Revision: D87946132
aobo-y
added a commit
to aobo-y/captum
that referenced
this pull request
Dec 1, 2025
Summary: following the discussion in D87818563, `MMImageMaskInput` can be generalized for non-LLM image model. So we rename the class as `ImageMaskInput` and make the `processor_fn` as optional. By default, if `processor_fn` is not given, the model input will be the (ablated) image Reviewed By: craymichael Differential Revision: D87946132
Contributor
|
This pull request has been merged in f536453. |
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Outdated suggestions cannot be applied.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.
Summary: following the discussion in D87818563,
MMImageMaskInputcan be generalized for non-LLM image model. So we rename the class asImageMaskInputand make theprocessor_fnas optional. By default, ifprocessor_fnis not given, the model input will be the (ablated) imageReviewed By: craymichael
Differential Revision: D87946132