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

关于效果和速度 #5

Open
fire717 opened this issue Sep 20, 2019 · 3 comments
Open

关于效果和速度 #5

fire717 opened this issue Sep 20, 2019 · 3 comments

Comments

@fire717
Copy link

fire717 commented Sep 20, 2019

感谢开源,但是我测试的时候效果不是很好,有如下两个问题:

1.打开视频第一帧必须有人脸,才能检测到进而追踪,否则就会一直没有检测结果,同时如果检测过程中丢失了人脸再出现,也依旧无法检测;
2.在rk3399的板子上fps只有30左右,离150fps还是有不少差距,是因为板子性能的问题吗?还是你们在移动端测试的机器比较好呢

@panda-lab
Copy link
Collaborator

@fire717 我们在Android上测试了,第一个问题没有出现,你看下是否移植有问题。第二个关于速度的问题,我们开源的是原始mtcnn,onet还是有一些大,可以考虑自己训练一个快速的onet,修改mobilenet等等。

@xuguozhi
Copy link

xuguozhi commented Jan 3, 2020

正准备入坑试试tracking,RK3399 30fps 会不会摄像头默认设置30fps?colotracker一帧大概多少时间?

@panda-lab
Copy link
Collaborator

我们测试在arm 835上可以做了100fps+

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

3 participants