Fix crash when negative prompt detects no objects#4
Open
jkukul wants to merge 1 commit intoschananas:mainfrom
Open
Fix crash when negative prompt detects no objects#4jkukul wants to merge 1 commit intoschananas:mainfrom
jkukul wants to merge 1 commit intoschananas:mainfrom
Conversation
When the negative prompt doesn't detect any objects in the image, GroundingDINO returns an empty tensor which causes SAM to fail with a reshape error. Now we check if boxes were detected before attempting segmentation. If no negative objects are detected, we skip the negative mask processing and use only the positive mask, which is the correct behavior since there's nothing to subtract.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When the negative prompt doesn't detect any objects in the image, GroundingDINO returns an empty tensor which causes SAM to fail with a reshape error. Now we check if boxes were detected before attempting segmentation. If no negative objects are detected, we skip the negative mask processing and use only the positive mask, which is the correct behavior since there's nothing to subtract.
Fixes #1