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

请问body,head,face这些数据集从哪来啊? #2

Open
zhangtao22 opened this issue Jul 16, 2018 · 2 comments
Open

请问body,head,face这些数据集从哪来啊? #2

zhangtao22 opened this issue Jul 16, 2018 · 2 comments

Comments

@zhangtao22
Copy link

zhangtao22 commented Jul 16, 2018

另外,他基于s3fd,控制低层负样本,找最大的负样本和正样本训练时怎么实现的啊,就是max-in-out这个?谢谢

@EricZgw
Copy link
Owner

EricZgw commented Jul 20, 2018

head、body是根据face衍生出来的,论文中叫PyramidAnchors。
我的理解是,低层时负样本(高层时正样本)情况复杂,因此max-in-out留给负样本3个通道(论文中实验得出)将其细分,选择其中最接近正样本的与正样本进行分类,提高分类能力。
@zhangtao22

@zhangtao22
Copy link
Author

maxout那个我实现了,只是没训出来。head,body是咋衍生出来的啊?

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