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

caffe matlab版的mtcnn 转ncnn 能够成功检测与同样的代码 c++ 版的mtcnn 转ncnn 后检测不到人脸是怎么回事。 #535

Closed
grainw opened this issue Aug 21, 2018 · 2 comments

Comments

@grainw
Copy link

grainw commented Aug 21, 2018

使用的是https://github.com/moli232777144/mtcnn_ncnn 这上面的程序,matlab版mtcnn 转ncnn 是项目自带的。c++版的是自己训练的。还了模型后检测不到东西。但是在caffe上能检测到。

@unanan
Copy link

unanan commented Aug 22, 2018

我另外的工程中(和你的不一样)也遇到了检不到脸的问题,后面发现是std::vector<Bbox> faces; mtcnn.detect(frame,faces);中的这个faces只能定义一次,如果每个loop重复定义,或者每个loop做了faces.resize(0);这种操作,就会有检不到脸的时候。
你看一下会不会对你的问题有所解决的提示?

@Xiangyu-CAS
Copy link

@grainw 刚解决了这个问题,这是conv和fc参数存储row-major和col-major不一致导致的,我们自己训练的MTCNN,做了weights转置后就可以正常工作了

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

4 participants