安裝Python基礎(chǔ)類庫

pip install numpy scipy pandas

pip install scikit-learn scikit-image

顯示已安裝類庫執(zhí)行命令pip list

安裝OpenCV 2.4.11

安裝文檔

http://docs.opencv.org/2.4/doc/tutorials/introduction/linux_install/linux_install.html

下載源代碼

https://github.com/opencv/opencv/archive/2.4.11.zip

unzip opencv-2.4.11.zip

cd opencv-2.4.11

安裝第三方依賴

sudo apt-get install build-essential sudo apt-get install cmake git libgtk2.0-dev pkg-config 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 mkdir release

cd release

cmake -DCMAKE_BUILD_TYPE=RELEASE -DCMAKE_INSTALL_PREFIX=/usr/local -DCUDA_GENERATION=Kelper ..

禁用CUDA，-DWITH_CUDA=NO

make -j8

sudo make install

驗(yàn)證opencv

安裝dlib

下載https://github.com/davisking/dlib/releases/download/v18.16/dlib-18.16.tar.bz2

tar xf dlib-18.16.tar.bz2

cd dlib-18.16/python_examples

mkdir build

cd build

cmake ../../tools/python

cmake --build . --config Release

sudo cp dlib.so /usr/local/lib/python2.7/dist-packages

驗(yàn)證dlib

安裝Torch (luajit方式)

git clone https://github.com/torch/distro.git --recursive

mv distro torch

cd torch

bash install-deps

./install.sh

另外一種安裝方式，使用lua代替luajit

git clone https://github.com/torch/distro.git --recursive

mv distro torch

cd torch

./clean.sh

TORCH_LUA_VERSION=LUA52 ./install.sh

運(yùn)行torch

source ~/.bashrc

th

退出torch

os.exit()

安裝torch第三方依賴，通過lua的包管理工具安裝

luarocks install dpnn nn optim optnet csvigo cutorch cunn fblualib torchx tds

顯示已安裝包luarocks list

安裝OpenFace

git clone https://github.com/cmusatyalab/openface.git

sudo python setup.py install

models/get-models.sh #下載訓(xùn)練好的模型數(shù)據(jù)

測(cè)試

從網(wǎng)上下載5張照片

f1.jpg

f2.jpg

f3.jpg

l1.jpg

l2.jpg

./demo/compare.py images/examples/f1.jpg images/examples/f2.jpg

./demo/compare.py images/examples/f1.jpg images/examples/f3.jpg

/demo/compare.py images/examples/f1.jpg images/examples/l1.jpg

./demo/compare.py images/examples/f1.jpg images/examples/l2.jpg

返回結(jié)果數(shù)值越小，代表兩張人臉越接近。

總結(jié)

以上是生活随笔為你收集整理的安装Openface，实现人脸比对的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。