Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

如何提升识别精度 #33

Open
anweihit opened this issue Jan 13, 2021 · 0 comments
Open

如何提升识别精度 #33

anweihit opened this issue Jan 13, 2021 · 0 comments

Comments

@anweihit
Copy link

大神好,感谢您的开源程序。近期我用你开源的代码训练了自己的模型,这个模型是一个具有5个分类的检测模型,通过maix go板上的摄像头进行实时的检测。但是,训练过程中的loss降到一定程度就不能降低了。最终结果的识别精度不好,主要的问题是对目标的分类总是搞错。
现在请教大神,我如何改进模型或者数据集才能提高识别精度?
在你的程序说明文档中有下面的提示:
OBJWEIGHT,NOOBJWEIGHT,WHWEIGHT used to balance precision and recall
我的理解是这两个参数可能会对识别精度有影响,但我清楚如何调整这两个参数。还有哪些设置参数会对精度有影响?
盼大神回复。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant