search

Qengineering / Face-Recognition-Raspberry-Pi-64-bits

Recognize 2000+ faces on your Raspberry Pi 4 with database auto-fill and anti-spoofing
https://qengineering.eu/deep-learning-examples-on-raspberry-32-64-os.html
BSD 3-Clause "New" or "Revised" License
69 stars 19 forks source link

windows 10 #5

Open MyraBaba opened 2 years ago

MyraBaba commented 2 years ago

Hi,

Is this FaceRecog could work on the windows 10 ?

I am a Unix/Linux guy and microsoft makes me crazy. Different compilers and not accepting the compiled libraries.

Is it possible to run on micro-soft win-dows?

Qengineering commented 2 years ago

In theory, it should work under Windows 10. You need to install the ncnn framework on your Windows machine first. Follow this link carefully. Then let OpenCV work in your VS2017. Now try to get images from your camera. Once this all works, you can transfer this repo to VS2017. It's all regular C++ code, nothing out of the ordinary. However, you must have advanced programming skills to transfer this entire project to Windows. Given the amount of time we spend maintaining the website and the GitHub repos, in addition to our core business, we, unfortunately, lack time to support this journey. It's your adventure.

MyraBaba commented 2 years ago

@Qengineering I started to port. I kinda work . UltrafaceMNN face detection.

But the results is very interesting what could be cause below picture with the model : RFB-320-quant-ADMM-32.mnn

Screen Shot 2021-09-29 at 21 39 08
MyraBaba commented 2 years ago

@Qengineering pthread is the looks main obstacle to port windows