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

How can get the high score? #48

Open
KRK11 opened this issue May 17, 2023 · 2 comments
Open

How can get the high score? #48

KRK11 opened this issue May 17, 2023 · 2 comments

Comments

@KRK11
Copy link

KRK11 commented May 17, 2023

I finish my CPN network like this, but it is only 0.553 mAP. Are there someone could give me advice about it?

@LiangYong1216
Copy link

改进改进

@KRK11
Copy link
Author

KRK11 commented May 18, 2023

改进改进
我发现了一个很大的问题,我原先数据集的生成是自己写的,生成局部的图片是可以把同一个人的所有关节点圈起来,最多外层再加10个像素点。
而这里的数据的生成却是把图片扩大到bbox的1.5倍左右,这就导致训练的时候模型确实能记住整个人在图片中点的大致关节点位置,但是无法预测到人物较近的情况。这样训练出来的模型的mAP值低的可怜只有0.003左右,甚至没能达到我原来的0.55。
这里关于数据集的这部分是怎么解决的,为什么训练结果如此截然不同?

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

2 participants