YOLO loader drops images that have no label file
Maintainers usually reply within 1 day
@guptakaran20 is already working on this.
Since Nov 11, 2026.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 72/100
- Issue type
- Bug
- Clarity
- Mostly clear
- Activity status
- Active
- Domain
- computer-vision, machine-learning
Research direction
Start by reading _add_to_dataset in yolo.py and compare how the COCO loader handles images without annotations. Check the loader tests for a way to cover a background image with no label file. Done means all four images are loaded and the unlabeled image contributes no boxes, so false positives can be counted.
Written by the indexing model from the issue text.
Description
Images that have no label file (YOLO background images) are skipped without any warning. In a test folder with 4 images in val, only 3 were loaded.
COCO keeps images without annotations, so the two loaders do not match.
I think it is because _add_to_dataset in yolo.py only adds a sample if both the image and the label file exist.
Possible fix: if the label file is missing, treat it as no boxes.
This matters because false positives on those images are not counted, so precision looks better than it is.
- Dominant language
- Python
- Stars
- 115
- Forks
- 117
- Avg merge
- 1d 14h
- Merged PRs (30d)
- 12
Getting set up
- No Dockerfile or Docker Compose file
- No pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from JdeRobot/PerceptionMetrics
-
COCO crowd annotations (iscrowd=1) are counted as ground truth, lowering detection recall and APOpen
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
JdeRobot/PerceptionMetrics#681 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
JdeRobot/PerceptionMetrics#679 ·
Maintainers usually reply within 1 day
-
pm_eval_model crashes with TypeError after the evaluation when --out_fname is not given (regression from #617)Possibly taken @Siddhanthguptaa claimed this 6 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
JdeRobot/PerceptionMetrics#675 ·
Maintainers usually reply within 1 day
-
Micro accuracy in segmentation is always the same as macro accuracyPossibly taken @guptakaran20 claimed this 6 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
JdeRobot/PerceptionMetrics#674 · 1 comment ·
Maintainers usually reply within 1 day
-
[Bug] Inference tab renders normalized tensors without inverse normalization.Possibly taken @divyanshAgarwal123 claimed this 67 days ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 85/100
JdeRobot/PerceptionMetrics#524 · 8 comments ·
Maintainers usually reply within 1 day
All issues in JdeRobot/PerceptionMetrics
Similar issues
-
Difficulty 1/5 Under an hour Newbie friendliness 85/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
OCA/account-invoicing#2529 ·
Maintainers usually reply within 1 day
-
area/ci
Difficulty 1/5 Under an hour Newbie friendliness 62/100
Maintainers usually reply within 1 day
-
ImageGen generate-batch aborts valid JSONL jobs containing a Unicode line separator in poster textOpenbug imagen skills
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Email validation accepts a trailing newlinePossibly taken @marcello-pichini claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day