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

This guide provides installation steps for Intel® Distribution of OpenVINO™ toolkit for Linux distributed through the APT repository.

Note

From the 2022.1 release, the OpenVINO™ Development Tools can only be installed via PyPI. If you want to develop or optimize your models with OpenVINO, see Install OpenVINO Development Tools for detailed steps.

Warning

By downloading and using this container and the included software, you agree to the terms and conditions of the software license agreements. Please review the content inside the <INSTALL_DIR>/licensing folder for more details.

System Requirements

The complete list of supported hardware is available in the Release Notes.

Operating Systems

  • Ubuntu 18.04 long-term support (LTS), 64-bit

  • Ubuntu 20.04 long-term support (LTS), 64-bit

Software

Install 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
    1. 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

OpenVINO will be installed in: /opt/intel/openvino_<VERSION>.<UPDATE>.<PATCH>

A symlink will be created: /opt/intel/openvino_<VERSION>

To Install the Latest Version

Run the following command:

sudo apt install openvino

To Install a Specific Version

  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-2022.1.0

To Check for Installed Packages and Versions

Run the following command:

apt list --installed | grep openvino

To Uninstall the Latest Version

Run the following command:

sudo apt autoremove openvino

To Uninstall a Specific Version

Run the following command:

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

Step 3 (Optional): Install OpenCV from APT

OpenCV is necessary to run C++ demos from Open Model Zoo. Some OpenVINO samples can also extend their capabilities when compiled with OpenCV as a dependency. OpenVINO provides a package to install OpenCV from APT:

To Install the Latest Version of OpenCV

Run the following command:

sudo apt install openvino-opencv

To Install a Specific Version of OpenCV

Run the following command:

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

Step 4 (Optional): Install Software Dependencies

After you have installed OpenVINO Runtime, if you decided to install OpenVINO Development Tools, make sure that you install external software dependencies first.

Refer to Install External Software Dependencies for detailed steps.

Step 5 (Optional): Configure Inference on Non-CPU Devices

To enable the toolkit components to use Intel® Gaussian & Neural Accelerator (GNA) on your system, follow the steps in GNA Setup Guide.

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

To perform inference on Intel® Neural Compute Stick 2 powered by the Intel® Movidius™ Myriad™ X VPU, follow the steps on NCS2 Setup Guide.

To install and configure your Intel® Vision Accelerator Design with Intel® Movidius™ VPUs, see the VPU Configuration Guide. After configuration is done, you are ready to run the verification scripts with the HDDL Plugin for your Intel® Vision Accelerator Design with Intel® Movidius™ VPUs.

Warning

While working with either HDDL or NCS, choose one of them as they cannot run simultaneously on the same machine.

What’s Next?

Now you may continue with the following tasks:

Additional Resources