🐛 Bugfix: [TensorRT Inference] Matching for bbox & label #480
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
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Outdated suggestions cannot be applied.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.
Hi, lyuwenyu
I found an issue during inference using the TensorRT model.
The problem occurs in the
drawfunction at line 188, wheretext=str(lab[i].item())is used, causing the labels and bounding boxes to not match correctly in the output.To resolve this, I applied
enumerate()to the box and aligned the index information of the box with the corresponding label.Below are the images showing the results before and after the bug fix:
The left image shows the result before the bug fix.
The right image shows the result after the bug fix.
Looking at the label indexes marked in the images, you can see that before the fix, only a single label was applied incorrectly to multiple detections.
Done!