modelscope / modelscope/ms-swift
qwen3-vl微调grounding任务，数据可以包含负样本吗
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
我想用swift对qwen3-vl微调一个grounding任务，看swift doc给的数据集例子，全都是单个或多个目标的，但我的训练集中会出现无目标的图像，同样，在infer的时候，希望有几个目标就数据几个目标框，对无目标的图像输出[]就可以了；想知道 ，训练集中可以有这种无目标的图像么
Contributor 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.
Research direction
Start with the Swift documentation's Qwen3-VL grounding dataset example and the related training and inference entry points. Determine whether images with no targets are supported and whether inference can represent them as []; done means documenting the supported behavior or identifying the required change.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100