OpenVINO - Download and Install

Previous
Quiz
Next

Supported Operating System - OpenVINO

Here’s the list of operating systems supported by OpenVINO −

  • Windows 11, 64-bit
  • Windows 10, 64-bit
  • Ubuntu 24.04 long-term support (LTS), 64-bit (Kernel 6.8+) (preview support)
  • Ubuntu 22.04 long-term support (LTS), 64-bit (Kernel 5.15+)
  • Ubuntu 20.04 long-term support (LTS), 64-bit (Kernel 5.15+)
  • macOS 12.6 and above, 64-bit and ARM64
  • CentOS 7
  • Red Hat Enterprise Linux 9.3-9.4, 64-bit
  • openSUSE Tumbleweed, 64-bit and ARM64
  • Ubuntu 20.04 ARM64

Download and Install the OpenVINO

Get the Intel Distribution of OpenVINO Toolkit from the Intel website. Currently if you don’t have an Intel account, you’ll need to create one, log in, and then move forward to the download page. Choose version 2024.3 TLS and enter your verification code.

The following instructions are given for Ubuntu 16.04 on a 64-bit OS.

Extract the installation Package

  • Open a cmd prompt window
  • Move to the directory where you downloaded the Intel Distribution of OpenVINO Toolkit for Linux. If you saved the package in your Downloads folder, run: cd ~/Downloads/ The file is typically named l_openvino_toolkit_p_<version>.tgz.
  • Extract the .tgz file: tar -xvzf l_openvino_toolkit_p_.tgz

Start Installing OpenVINO

Open a terminal, move to the folder created after extraction, and run the installation command.

Choice 1 − Use the GUI Installation Wizard: sudo ./install_GUI.sh

Choice 2 − Follow the Command-Line Instructions: sudo ./install.sh

When installed as root the default installation directory for OpenVINO is /opt/intel/openvino_<version>/

Complete the installation process, indicating that OpenVINO has been installed.

Install External Software Requirements

Note: If you install OpenVINO in a directory other than the default, then replace /opt/intel with the path to your installation directory.

The required dependencies are −

  • Intel-optimized build of OpenCV library
  • Deep Learning Inference Engine
  • Deep Learning Model Optimizer tools
    • 1.Change to the install_dependencies path: cd /opt/intel/openvino/install_dependencies
    • 2.Run a code to download and install the external software requirements: sudo -E ./install_openvino_dependencies.sh

Set the Environment Variables

Before you compile and run the OpenVINO application, you need to update multiple environment variables.

Use these instructions to set the env variables −

  • Open the .bashrc file in <user_directory>: vi /.bashrc
  • Add these commands at the end of the file: source /opt/intel/openvino/bin/setupvars.sh
  • Save and close the file by pressing the Esc key and Enter : wq
  • To test your change, Open a new terminal. you'll notice: [setupvars.sh] OpenVINO environment is ready.

Set Up the Model Optimizer

  • Move to the prerequisites path of Model Optimizer: cd/opt/intel/openvino/deployment_tools/model_optimizer/install_prerequisites
  • Execute these codes to set the Model Optimizer for Caffe, TensorFlow, MXNet, Kaldi, and ONNX: $ sudo ./install_prerequisites.sh

You can also run the specific version as required −

  • Kaldi: sudo ./install_prerequisites_kaldi.sh
  • MXNet: sudo ./install_prerequisites_mxnet.sh
  • TensorFlow: sudo ./install_prerequisites_tf.sh
  • ONNX: sudo ./install_prerequisites_onnx.sh
  • Caffe: sudo ./install_prerequisites_caffe.sh
Print Page
Previous
Next
Advertisements