OpenVINO - Tauvic/DriverAwareness GitHub Wiki

Install open VINO on Windows 10

https://docs.openvinotoolkit.org/2021.1/openvino_docs_install_guides_installing_openvino_windows.html

System

  • OS: Windows 10 Pro 64 bits
  • Processor: Intel i7- 6820HQ 2.7 GHz
  • Memory: 16GB
  • Disk: 237GB / 172GB Free

Steps: Takes about an hour

  • Install the Intel® Distribution of OpenVINO™ toolkit core components
    • Choose:
      • Operating system: Windows
      • Distribution: Web and Local install
      • Installer type: Local
    • Select the right distribution (we use precompiled by Microsoft for Windows)
    • Register with Microsoft and make a note of serial number (dont worry, you get an email with the serial number)
    • Download the software
    • Install (check all options)
  • Install Microsoft Visual Studio C++, Python
    • goto Download and select Community version
    • install check C++ and Python (requirers 3.63GB disk space)
  • Install CMake link (add CMake to PATH for all users)
  • Install Python 3.6-3.8 (https://www.python.org/downloads/windows/)
    • make sure you click the option to add the application to your PATH environment variable.
  • Restart the computer
  • Set Environment variables (only required when you changed installation path)

Build and run the demo's

  • Build and prepare procedure
  • C:\Program Files (x86)\Intel\openvino_2021\deployment_tools\open_model_zoo\demos\build_demos_msvc.bat
  • Set environment variables: "C:\Program Files (x86)\Intel\openvino_2021.1.110\bin\setupvars.bat"
  • Goto directory: %USERPROFILE%\Documents\Intel\OpenVINO\omz_demos_build\intel64\Release
  • Download all models: python "%INTEL_OPENVINO_DIR%\deployment_tools\tools\model_downloader\downloader.py" -all
  • Run https://www.youtube.com/watch?v=LtspLbUogZI&list=PLg-UKERBljNxdIQir1wrirZJ50yTp4eHv&index=50

Gaze Estimation Demo link

gaze_estimation_demo -i 0 ^
   -m ./intel/gaze-estimation-adas-0002/FP16/gaze-estimation-adas-0002.xml ^
   -m_fd ./intel/face-detection-adas-0001/FP16/face-detection-adas-0001.xml ^
   -m_hp ./intel/head-pose-estimation-adas-0001/FP16/head-pose-estimation-adas-0001.xml ^
   -m_lm ./intel/facial-landmarks-35-adas-0002/FP16/facial-landmarks-35-adas-0002.xml ^
   -m_es ./public/open-closed-eye-0001/open-closed-eye.onnx

Object Detection RetinaFace Demo

Action Recognition Python link