Megvii-BaseDetection / Megvii-BaseDetection/YOLOX

Model only predicting singe class despite of being 3 classes

Open
#1,430 0 comments 0 reactions 0 assignees View on GitHub

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

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.