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

This guide provides detailed steps for installing OpenVINO™ Runtime through the APT repository and guidelines for installing OpenVINO Development Tools.

Note

From the 2022.1 release, OpenVINO™ Development Tools can be installed via PyPI only. See Install OpenVINO Development Tools for more information.

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

CMake 3.13 or higher, 64-bit
GCC 7.5.0 (for Ubuntu 18.04) or GCC 9.3.0 (for Ubuntu 20.04)
Python 3.6 - 3.9, 64-bit

Installing OpenVINO Runtime¶

Step 1: Set Up the OpenVINO Toolkit APT Repository¶

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

Add the repository via the following command:

Ubuntu 18

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

Ubuntu 20

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

Update the list of packages via the update command:
```
sudo apt update
```
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¶

Get a list of OpenVINO packages available for installation:
```
sudo apt-cache search openvino
```

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): Configure Inference on Non-CPU Devices¶

GNA

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

GPU

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

NCS 2

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

VPU

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.

Installing OpenVINO Development Tools¶

Note

From the 2022.1 release, the OpenVINO™ Development Tools can be installed via PyPI only.

To install OpenVINO Development Tools, do the following steps:

Install OpenVINO Runtime if you haven’t done it yet.
Install External Software Dependencies.
See the For C++ Developers section in Install OpenVINO Development Tools for detailed steps.

What’s Next?¶

Now you may continue with the following tasks:

To convert models for use with OpenVINO, see Model Optimizer Developer Guide.
See pre-trained deep learning models in our Open Model Zoo.
Try out OpenVINO via OpenVINO Notebooks.
To write your own OpenVINO™ applications, see OpenVINO Runtime User Guide.
See sample applications in OpenVINO™ Toolkit Samples Overview.

Additional Resources¶

Intel® Distribution of OpenVINO™ toolkit home page: https://software.intel.com/en-us/openvino-toolkit.
For IoT Libraries & Code Samples see the Intel® IoT Developer Kit.

Prev Next