You can install the following nuget packages.

• DlibDotNet
  • For only CPU.
• DlibDotNet.CUDA92
  • For computer installed CUDA 9.2.
• DlibDotNet.CUDA100
  • For computer installed CUDA 10.0.
• DlibDotNet.MKL
  • For intel CPU and use Intel Math Kernel Library
• DlibDotNet-ARM
  • For only ARM CPU. It is alpha release and experimental.

• Visual C++ 2017 Redistributable Package
• (Optional for CUDA package) NVIDIA Driver
  • We recommend to install latest driver suitable your graphic card and check whether availability CUDA.
• (Optional for CUDA package) CUDA
• (Optional for CUDA package) cuDNN
  • Install it to CUDA_HOME directory
• (Optional for MKL pacakge) Intel Math Kernel Library
  • Nuget package bundles the following libraries and it is not necessary to install Intel Math Kernel Library.
    • libiomp5md.dll
    • mkl_core.dll
    • mkl_def.dll
    • mkl_intel_thread.dll

• X11
  • Ubuntu: sudo apt-get install libx11-6
• OpenBLAS
  • Ubuntu: sudo apt-get install libopenblas-dev
• libgdiplus
  • sudo apt-get install libgdiplus
• (Optional for CUDA package) CUDA
  • We recommend to install latest driver suitable your graphic card and check whether availability CUDA.
• (Optional for CUDA package) cuDNN
• (Optional for MKL pacakge) Intel Math Kernel Library
  • But apt-get support to install Intel Math Kernel Library

$ apt-get update $ apt install -y wget apt-transport-https $ wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS-2019.PUB $ apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS-2019.PUB $ sh -c 'echo deb https://apt.repos.intel.com/mkl all main > /etc/apt/sources.list.d/intel-mkl.list' $ apt-get update $ apt-get install -y intel-mkl-64bit-2019.0-045

• X11
  • Install from here
  • brew cask install xquartz
• libgdiplus
  • brew install mono-libgdiplus
• (Optional for MKL pacakge) Intel Math Kernel Library
  • Install Intel MKL 2019 Initial Release

PM> Install-Package DlibDotNet 

> dotnet add package DlibDotNet