Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
yolox multi detection head问题
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
我想用yolox实现多数据集检测问题, objects365,openimages,coco等数据集公用1个backbone，分布用不同的检测头部输出对应数据集的预测结果。请问如何添加多个检测头部？ 给给个示例嘛？
谢谢，祝您工作愉快！
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
The issue describes sharing one backbone across Objects365, OpenImages, and COCO while using separate detection heads, but names no files, tests, or entry points. Start by locating the model and training entry points for dataset-specific prediction heads. Done would require an agreed design and a working example covering the requested multi-dataset setup.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100