Install OpenVINO™ Runtime on Linux From YUM Repository¶

Note

Note that the YUM distribution:

offers C/C++ APIs only
does not offer support for GNA and NPU inference
additionally includes code samples

System Requirements

Full requirement listing is available in:

Note

Installing OpenVINO from YUM is only supported on RHEL 8.2 and higher versions. CentOS 7 is not supported for this installation method.

Processor Notes

To see if your processor includes the integrated graphics technology and supports iGPU inference, refer to:

Product Specifications

Software

Install OpenVINO Runtime¶

Step 1: Set Up the Repository¶

Create a YUM repository file (openvino-2023.repo) in the /tmp directory as a normal user:

tee > /tmp/openvino-2023.repo << EOF
[OpenVINO]
name=Intel(R) Distribution of OpenVINO 2023
baseurl=https://yum.repos.intel.com/openvino/2023
enabled=1
gpgcheck=1
repo_gpgcheck=1
gpgkey=https://yum.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
EOF

Move the new openvino-2023.repo file to the YUM configuration directory, i.e. /etc/yum.repos.d:
```
sudo mv /tmp/openvino-2023.repo /etc/yum.repos.d
```
Verify that the new repository is set up properly.
```
yum repolist | grep -i openvino
```
You will see the available list of packages.

To list available OpenVINO packages, use the following command:

yum list 'openvino*'

Step 2: Install OpenVINO Runtime Using the YUM Package Manager¶

Install OpenVINO Runtime¶

The Latest Version

Run the following command:

sudo yum install openvino

A Specific Version

Run the following command:

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

For example:

sudo yum install openvino-2023.1.0

Check for Installed Packages and Version¶

Run the following command:

yum list installed 'openvino*'

Note

You can additionally install Python API using one of the alternative methods (conda or pip).

Congratulations! You’ve just Installed OpenVINO! For some use cases you may still need to install additional components. Check the list of additional configurations to see if your case needs any of them.

With the YUM distribution, you can build OpenVINO sample files, as explained in the guide for OpenVINO sample applications. For C++ and C, just run the build_samples.sh script:

C++

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

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

Uninstalling OpenVINO Runtime¶

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

The Latest Version

sudo yum autoremove openvino

A Specific Version

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

For example:

sudo yum autoremove openvino-2023.1.0

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:

Try the C++ Quick Start Example for step-by-step instructions on building and running a basic image classification C++ application.
Visit the Samples page for other C++ example applications to get you started with OpenVINO, such as:
- Basic object detection with the Hello Reshape SSD C++ sample
- Automatic speech recognition C++ sample

You can also try the following things:

Learn more about OpenVINO Workflow.
To prepare your models for working with OpenVINO, see Model Preparation.
See pre-trained deep learning models in our Open Model Zoo.
Learn more about Inference with OpenVINO Runtime.
See sample applications in OpenVINO toolkit Samples Overview.
Take a glance at the OpenVINO product home page: https://software.intel.com/en-us/openvino-toolkit.