biubug6 / Pytorch_Retinaface

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Could someone convert the detector code to c++?

shivabohemian opened this issue · comments

Could someone convert the detector code to c++?

I made a C++ implementation of it. Currently it seems that I fucked up somewhere (Segmentation Fault) but it was previously functional. Here you can find the repo.

In order to use the cmake compilation, please remove the lines regarding the compilation of full target, since these are files that I can't share.

Another requirement is the unzipping of the model in model path. This was tested in Ubuntu 20.04 LTS environment with openCV 4 installed globally.

Edit: There were lots of errors actually (detection was only working on square images). I've made the necessary fixes on another project using this implementation and will update the provided one soon