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 I detection many people? #1

Open
getengqing opened this issue Oct 28, 2016 · 13 comments
Open

How can I detection many people? #1

getengqing opened this issue Oct 28, 2016 · 13 comments

Comments

@getengqing
Copy link

Hello, your demo detects one people, when I want to detection many people, so how do it?

@DuinoDu
Copy link
Owner

DuinoDu commented Oct 28, 2016

I can detect many people using my test image. So would you mind show me your test image?

@getengqing
Copy link
Author

img_screenshot_28 10 2016

@DuinoDu
Copy link
Owner

DuinoDu commented Oct 29, 2016

It does detect two faces, haha?

@getengqing
Copy link
Author

But there are many error rectangular box。。。

@JianjinChen
Copy link

I have solved the problem by just commenting out codes in line 553-554 of “demo.py”.
image
Now, it's ok to detect two or more faces, without error rectangular boxes!
image

@DuinoDu
Copy link
Owner

DuinoDu commented Dec 7, 2016

Thank you!

@kli-casia
Copy link

kli-casia commented Dec 30, 2016

@DuinoDu @JianjinChen 您好,您这个python的版本和作者公布的matlab 版本结果差别大吗?

@DuinoDu
Copy link
Owner

DuinoDu commented Dec 30, 2016

差别还好吧,没有具体地比较

@jianbaba
Copy link

jianbaba commented Jul 7, 2017

请问有没有训练代码? @DuinoDu

@xiao1228
Copy link

同问,谢谢 @DuinoDu

@DuinoDu
Copy link
Owner

DuinoDu commented Jul 13, 2017

我正在写这部分的代码 @jianbaba @xiao1228

@hust-kevin
Copy link

@DuinoDu 请问训练的代码现在写完了吗

@xuexue577
Copy link

How does your code work?I've been reporting errors!I want to communicate with you, may I?Thank you very much。 @DuinoDu @JianjinChen @jianbaba

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

8 participants