Add feature extraction support for image models#2255
Merged
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Member
|
No need to change the testing suite for this, as it's gonna be undergoing some refactoring |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
This PR adds support for image models in ORTModelForFeatureExtraction, specifically addressing ViT and other visual models. The implementation modifies the forward method to dynamically handle both text and image inputs by detecting the presence of image-specific input keys like 'pixel_values'. This allows users to seamlessly use ORTModelForFeatureExtraction for both text and image feature extraction tasks without requiring a separate class structure. Tests have been updated to properly validate this functionality across all supported architectures, including Vision Transformer (ViT) models.
Fixes # (issue)
Fixes the issue : #2226
Before submitting