Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
Model only predicting singe class despite of being 3 classes
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
I am training yoloxs to train on 3 classes but after training.py when I run demo.py for checking the trained model it always return just 1 classes. Any clue how we can dubugg this issue? (Same dataset when trained with yolov5 is giving decent results)
Contributor guide
No contributing guide indexed for this repository
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.
Research direction
Start by reproducing the issue with the dataset and trained checkpoint using training.py and demo.py. Inspect how the three classes are configured and passed between those entry points, then compare the demo output with the YOLOv5 result. Done means the YOLOX demo identifies all three classes consistently.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100