Install Intel® Distribution of OpenVINO™ Toolkit for Linux Using APT Repository

With the OpenVINO™ 2022.3 release, you can install OpenVINO Runtime on Linux using the APT repository. OpenVINO™ Development Tools can be installed via PyPI only. See Installing Additional Components for more information.

See the Release Notes for more information on updates in the latest release.

Installing OpenVINO Runtime from APT is recommended for C++ developers. If you are working with Python, the PyPI package has everything needed for Python development and deployment on CPU and GPUs. Visit the Install OpenVINO from PyPI page for instructions on how to install OpenVINO Runtime for Python using PyPI.

Warning

By downloading and using this container and the included software, you agree to the terms and conditions of the software license agreements.

Prerequisites

Full requirement listing is available in:
System Requirements Page

Processor graphics are not included in all processors. See Product Specifications for information about your processor.

Installing OpenVINO Runtime

Step 1: Set Up the OpenVINO Toolkit APT Repository

  1. Install the GPG key for the repository

    1. Download the GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB

      You can also use the following command:

      wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB

    2. Add this key to the system keyring:

      sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB

      Note

      You might need to install GnuPG:

      sudo apt-get install gnupg

  2. Add the repository via the following command:

    echo "deb https://apt.repos.intel.com/openvino/2022 bionic main" | sudo tee /etc/apt/sources.list.d/intel-openvino-2022.list

    echo "deb https://apt.repos.intel.com/openvino/2022 focal main" | sudo tee /etc/apt/sources.list.d/intel-openvino-2022.list

  3. Update the list of packages via the update command:

    sudo apt update

  4. Verify that the APT repository is properly set up. Run the apt-cache command to see a list of all available OpenVINO packages and components:

    apt-cache search openvino

Step 2: Install OpenVINO Runtime Using the APT Package Manager

Install OpenVINO Runtime

Run the following command:

sudo apt install openvino

  1. Get a list of OpenVINO packages available for installation:

    sudo apt-cache search openvino

  2. Install a specific version of an OpenVINO package:

    sudo apt install openvino-<VERSION>.<UPDATE>.<PATCH>

    For example:

    sudo apt install openvino-2022.3.0

Note

You can use --no-install-recommends option to install only required packages. Keep in mind that the build tools must be installed separately if you want to compile the samples.

Check for Installed Packages and Versions

Run the following command:

apt list --installed | grep openvino

Step 3 (Optional): Install Additional Components

OpenVINO Development Tools is a set of utilities for working with OpenVINO and OpenVINO models. It provides tools like Model Optimizer, Benchmark Tool, Post-Training Optimization Tool, and Open Model Zoo Downloader. If you installed OpenVINO Runtime using APT, OpenVINO Development Tools must be installed separately.

See the For C++ Developers section on the Install OpenVINO Development Tools page for instructions.

Step 4 (Optional): Configure Inference on Non-CPU Devices

To enable the toolkit components to use processor graphics (GPU) on your system, follow the steps in GPU Setup Guide.

Step 5: Build Samples

To build the C++ or C sample applications for Linux, run the build_samples.sh script:

/usr/share/openvino/samples/cpp/build_samples.sh

/usr/share/openvino/samples/c/build_samples.sh

For more information, refer to Build the Sample Applications on Linux.

Uninstalling OpenVINO Runtime

To uninstall OpenVINO Runtime via APT, run the following command based on your needs:

sudo apt autoremove openvino

sudo apt autoremove openvino-<VERSION>.<UPDATE>.<PATCH>

For example:

sudo apt autoremove openvino-2022.3.0

What’s Next?

Now that you’ve installed OpenVINO Runtime, you’re ready to run your own machine learning applications! Learn more about how to integrate a model in OpenVINO applications by trying out the following tutorials:

You can also try the following things: