Openface: Instalasi di Ubuntu 18.04 Desktop

Sumber:

• https://github.com/TadasBaltrusaitis/OpenFace/wiki/Unix-Installation
• https://github.com/TadasBaltrusaitis/OpenFace/wiki/Model-acquisition

Instalasi Ubuntu

Membutuhkan

• gcc
• clang
• cmake
• opencv
• tbb
• boost

Advanced Ubuntu installation

For Unix based systems and different compilers, I included Cmake files for cross-platform and cross-IDE support.

This code has been tested on Ubuntu 14.04.1 with GCC, and on 15.10 with Clang 3.7.1.

You can also run the install.sh script for installing on Ubuntu 16.04 (it combines the following steps into one script)

Dependency installation

This requires cmake, OpenCV 3.1.0 (or newer), tbb and boost.

To acquire all of the dependencies follow the instructions pertaining to your Operating System: Ubuntu gcc compiler instructions

   Get newest GCC, done using:

sudo su
apt update
apt -y install build-essential cmake libopenblas-dev liblapack-dev \
git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev \
python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev \
libtiff-dev libdc1394-22-dev checkinstall

Instalasi OpenCV

wget https://github.com/opencv/opencv/archive/3.4.1.zip
sudo unzip 3.4.1.zip
cd opencv-3.4.1
mkdir build
cd build

 cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local -D WITH_TBB=ON -D BUILD_SHARED_LIBS=OFF ..
 make -j2
 sudo make install

Instalasi boost

sudo apt-get install libboost1.55-all-dev
sudo apt-get install libboost-all-dev

Ubuntu clang compiler instructions

Install LLVM, Clang & libc++

apt update
apt -y install build-essential llvm clang libc++-dev libc++abi-dev \
cmake libopenblas-dev liblapack-dev git libgtk2.0-dev pkg-config \
libavcodec-dev libavformat-dev libswscale-dev python-dev python-numpy \
libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev \
libdc1394-22-dev checkinstall

Install OpenCV 3.4.1

cd /usr/local/src/
wget https://github.com/opencv/opencv/archive/3.4.1.zip
sudo unzip 3.4.1.zip
cd opencv-3.4.1
mkdir build
cd build

   4.4 Build it using:

cmake -D CMAKE_CXX_COMPILER=clang++ -D CMAKE_CXX_FLAGS="-std=c++11 -stdlib=libc++ -I/usr/include/libcxxabi" -D CMAKE_EXE_LINKER_FLAGS="-std=c++11 -stdlib=libc++ -lc++abi" -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local -D OPENCV_EXTRA_MODULES_PATH=<path to opencv_contrib modules> -D BUILD_TIFF=ON -D WITH_V4L=ON -D WITH_GTK=ON -D BUILD_opencv_dnn=OFF -D WITH_TBB=ON ..

# gagal di /usr/include/libcxxabi - tidak ada, harusnya ada libc++abi

make -j2
make install

   Get Boost 1.61.0:

   5.1 Install boost dependency:

   sudo apt-get install libbz2-dev

   5.2 Get the boost source:

   Download boost_1_61_0.tar.bz2.

   In the directory where you want to put the boost installation, execute:

   tar --bzip2 -xf /path/to/boost_1_61_0.tar.bz2

   5.3 Build and install:

    cd path/to/boost_1_61_0
    ./bootstrap.sh --with-toolset=clang --prefix=/usr/local
    ./b2 toolset=clang cxxflags="-std=c++11 -stdlib=libc++ -I/usr/include/libcxxabi" linkflags="-stdlib=libc++" --prefix=/usr/local -j 10 define=BOOST_SYSTEM_NO_DEPRECATED stage release
    sudo ./b2 install toolset=clang cxxflags="-std=c++11 -stdlib=libc++" linkflags="-stdlib=libc++" --prefix=/usr/local

Actual OpenFace installation

   Get OpenFace

   git clone https://github.com/TadasBaltrusaitis/OpenFace.git

   Create an out-of-source build directory to store the compiled artifacts:

    cd OpenFace
    mkdir build
    cd build

   Compile the code using instructions pertaining to your operating system:

       Ubuntu 14.04

       cmake -D CMAKE_BUILD_TYPE=RELEASE ..

       make

       Ubuntu 15.10

       cmake -D CMAKE_CXX_COMPILER=clang++ -D CMAKE_CXX_FLAGS="-std=c++11 -stdlib=libc++ -I/usr/include/libcxxabi" -D CMAKE_EXE_LINKER_FLAGS="-std=c++11 -stdlib=libc++ -lc++abi" -D CMAKE_BUILD_TYPE=RELEASE ..

       make

   Test it with

       for videos:

       ./bin/FaceLandmarkVid -f "../samples/changeLighting.wmv" -f "../samples/2015-10-15-15-14.avi"

       for images:

       ./bin/FaceLandmarkImg -fdir "../samples/" -wild

       for multiple faces in videos:

       ./bin/FaceLandmarkVidMulti -f ../samples/multi_face.avi

       for feature extraction (facial landmarks, head pose, AUs, gaze and HOG and similarity aligned faces):

       ./bin/FeatureExtraction -verbose -f "../samples/default.wmv"

Troubleshooting X server

If you experience a problem with "cannot connect to X server" when trying to execute the tracker, a solution can be found here http://askubuntu.com/questions/64820/wkhtmltopdf-wkhtmltoimage-cannot-connect-to-x-server, to resolve run: apt-get install xvfb Anaconda

When Anaconda is installed, somehow OpenCV finds the outdated GCC 4.x instead of GCC 5.4, according to: https://stackoverflow.com/questions/40322301/compile-opencv-3-on-ubuntu-16-04-linking-error-usr-lib-x86-64-linux-gnu-libsox

This results in OpenFace giving the error: usr/lib/x86_64-linux-gnu/libsoxr.so.0: undefined reference to `GOMP_parallel@GOMP_4.0' collect2: error: ld returned 1 exit status

Referensi

• https://github.com/TadasBaltrusaitis/OpenFace/wiki/Unix-Installation