Grad-CAM explanation in the classification inference UI - #178
Open
Alvin-Nahabwe wants to merge 1 commit into
Open
Grad-CAM explanation in the classification inference UI#178Alvin-Nahabwe wants to merge 1 commit into
Alvin-Nahabwe wants to merge 1 commit into
Conversation
The Inference tab's image-classification panel gains an "Explain prediction (Grad-CAM heatmap)" checkbox. When ticked, the app calls the new /explain/image-classification endpoint instead of plain inference, shows the predicted class with its confidence, and renders the returned heatmap overlay so a non-expert user can see which regions drove the prediction. Verified with parse() on both changed files. Depends on the API-side endpoint (companion PR on no-code-transformers). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The Inference tab's image-classification panel gains an "Explain prediction (Grad-CAM heatmap)" checkbox. When ticked:
/explain/image-classificationinstead of plain inference,A non-expert user gets a visual answer to "why did it say that?" — the point of explainability on this platform.
Verified
parse()passes on both changed files. End-to-end behaviour depends on the API endpoint (verified separately on CPU).