Fix batch object detection 31356 #39306
Open
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
z-pandeyji
force-pushed
the
fix-batch-object-detection-31356
branch
from
c766412 to
cb00bc7
Compare
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Outdated suggestions cannot be applied.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.
@amyeroberts @Narsil
Fixes #31356
Issue: Object Detection Pipeline only outputs first element when batching
Solution
The Object Detection Pipeline now correctly handles batched inputs, returning results for all images in the batch instead of just the first one.
Verification
Before/After
Before:
detector([img1, img2, img3])→ Returns results for only img1After:
detector([img1, img2, img3])→ Returns results for all 3 imagesTechnical Details
src/transformers/pipelines/object_detection.pyImpact