Install Intel® Distribution of OpenVINO™ toolkit for Linux* Using YUM Repository¶
This guide provides installation steps for the Intel® Distribution of OpenVINO™ toolkit for Linux* distributed through the YUM repository.
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 <openvino_install_root>/licensing
folder for more details.
Note
Intel® Graphics Compute Runtime for OpenCL™ is not a part of OpenVINO™ YUM distribution. You can install it from the Intel® Graphics Compute Runtime for OpenCL™ GitHub repo.
Note
Only runtime packages are available via the YUM repository.
System Requirements¶
The complete list of supported hardware is available in the Release Notes.
Operating Systems
CentOS 7.6, 64-bit
Included with Runtime Package¶
The following components are installed with the OpenVINO runtime package:
Component |
Description |
---|---|
The engine that runs a deep learning model. It includes a set of libraries for an easy inference integration into your applications. |
|
OpenCV* community version compiled for Intel® hardware. |
|
Deep Learning Stream (DL Streamer) |
Streaming analytics framework, based on GStreamer, for constructing graphs of media analytics components. For the DL Streamer documentation, see DL Streamer Samples , API Reference , Elements , Tutorial . |
Install Packages¶
Set up the Repository¶
Note
You must be logged in as root to set up and install the repository.
Configure YUM with the OpenVINO repository to install OpenVINO. You have two options for this, using the yum-config-manager
or manually by creating a text file and pointing YUM to the file.
OPTION 1: Import the
.repo
file using theyum-config-manager
:yum-utils
must be installed on your system. If it’s not currently installed, run the command:sudo yum install yum-utils
Add repository using the
yum-config-manager
:sudo yum-config-manager --add-repo https://yum.repos.intel.com/openvino/2021/setup/intel-openvino-2021.repo
Import the gpg public key for the repository:
sudo rpm --import https://yum.repos.intel.com/openvino/2021/setup/RPM-GPG-KEY-INTEL-OPENVINO-2021
OPTION 2: Create the repository file manually:
Create the YUM repo file in the /tmp directory as a normal user:
tee > /tmp/openvino-2021.repo << EOF [intel-openvino-2021] name=Intel(R) Distribution of OpenVINO 2021 baseurl=https://yum.repos.intel.com/openvino/2021 enabled=1 gpgcheck=1 gpgkey=file:///etc/pki/rpm-gpg/RPM-GPG-KEY-INTEL-OPENVINO-2021 EOF
Move the newly created openvino-2021.repo file to the YUM configuration directory /etc/yum.repos.d:
sudo mv /tmp/openvino-2021.repo /etc/yum.repos.d
Import the gpg public key for the repository:
sudo rpm --import https://yum.repos.intel.com/openvino/2021/setup/RPM-GPG-KEY-INTEL-OPENVINO-2021
Verify that the new repo is properly setup¶
Run the following command:
yum repolist | grep -i openvino
Results:
intel-openvino-2021 Intel(R) Distribution of OpenVINO 2021
Install Runtime Packages Using the YUM Package Manager¶
Intel® OpenVINO will be installed in: /opt/intel/openvino_<VERSION>.<UPDATE>.<BUILD_NUM>
A symlink will be created: /opt/intel/openvino_<VERSION>
To install the latest version¶
To install the full runtime version of the OpenVINO package:
sudo yum install intel-openvino-runtime-centos7
To install a specific version¶
To install the full runtime version of the OpenVINO package:
sudo yum install intel-openvino-runtime-centos7-<VERSION>.<UPDATE>.<BUILD_NUM>
Examples¶
sudo yum install intel-openvino-runtime-centos7-2021.3.394
To check for installed packages and version¶
To check a specific version of an OpenVINO package:
yum list installed intel-openvino*
To Uninstall a specific version¶
To uninstall a specific full runtime package:
sudo yum autoremove intel-openvino-runtime-centos<OS_VERSION>-<VERSION>.<UPDATE>.<BUILD_NUM>
Additional Resources
Intel® Distribution of OpenVINO™ toolkit home page: https://software.intel.com/en-us/openvino-toolkit
OpenVINO™ toolkit online documentation: https://docs.openvinotoolkit.org
For more information on Sample Applications, see the Inference Engine Samples Overview.
For IoT Libraries & Code Samples see the Intel® IoT Developer Kit.