git clone : https://github.com/davidsandberg/facenet
tensorflow facenet
use MNCNN extract faceinfo to feed Facenet
run align_dataset_mtcnn.py
no model name cv2
use mac air install brew
brew install opencv3
mind the python2 or python3
tensorflow;scipy;numpy;matplotlib are required
run align_dataset_mtcnn.py with pictures and outputdir again
linux
install opencv3
sudo apt-install update
报错
修改源 /etc/apt/sources.list
deb http://http.kali.org/kali kali-rolling main contrib non-free
deb http://old.kali.org/kali sana main non-free contrib
再次执行 sudp apt-install update
报其他错误
添加公钥
sudo apt-key adv –recv-keys –keyserver keyserver.Ubuntu.com 7D8D0BF6
sudo apt-get update
sudo apt-get install build-essential
sudo apt-get install cmake git libgtk2.0-dev pkg-config
sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev
sudo apt-get install python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libjasper-dev libdc1394-22-dev
http://blog.youkuaiyun.com/zhangxb35/article/details/50358674