Install OpenVINO™ Runtime on Linux from an Archive File¶
With the OpenVINO™ 2022.2 release, you can download and use archive files to install OpenVINO Runtime.
You can also check the Release Notes for more information on updates in this release.
Since the OpenVINO™ 2022.1 release, the following development tools: Model Optimizer, Post-Training Optimization Tool, Model Downloader and other Open Model Zoo tools, Accuracy Checker, and Annotation Converter can be installed via pypi.org only.
Ubuntu 18.04 long-term support (LTS), 64-bit
Ubuntu 20.04 long-term support (LTS), 64-bit
Since the OpenVINO™ 2022.1 release, CentOS 7.6, 64-bit is not longer supported.
Optimized for these processors:
6th to 12th generation Intel® Core™ processors and Intel® Xeon® processors
3rd generation Intel® Xeon® Scalable processor (formerly code named Cooper Lake)
Intel® Xeon® Scalable processor (formerly Skylake and Cascade Lake)
Intel Atom® processor with support for Intel® Streaming SIMD Extensions 4.1 (Intel® SSE4.1)
Intel Pentium® processor N4200/5, N3350/5, or N3450/5 with Intel® HD Graphics
Intel® Iris® Xe MAX Graphics
Intel® Neural Compute Stick 2
Intel® Vision Accelerator Design with Intel® Movidius™ VPUs
Processor graphics are not included in all processors. See Product Specifications for information about your processor.
Installing OpenVINO Runtime¶
Before you start your journey with installation of the Intel® Distribution of OpenVINO™ toolkit, we encourage you to check the code samples in C, C++, Python and notebook tutorials, so you could see all the amazing things that you can achieve with our tool.
Step 1: Download and Install the OpenVINO Package¶
Select and download the OpenVINO™ archive files from Intel® Distribution of OpenVINO™ toolkit download page. There are typically two files for you to download:
l_openvino_toolkit_<operating system>_<release version>_<package ID>_x86_64.tgz l_openvino_toolkit_<operating system>_<release version>_<package ID>_x86_64.tgz.sha256
.sha256file is used to verify the success of the download process.
Open a command prompt terminal window. You can use the keyboard shortcut: Ctrl+Alt+T
Change the directory to where you downloaded the archive files.
For example, if you downloaded the files to the current user’s
Downloadsdirectory, use the following command:
To verify the package by using the
sha256sum -с <archive name>.tgz.sha256
If any error message appears, check your network connections, re-download the correct files, and make sure the download process completes successfully.
Extract OpenVINO files from the
tar xf <archive name>.tgz -C <destination_dir>
<destination_dir>is the directory that you extract OpenVINO files to. You’re recommended to set it as:
For root users or administrators:
For regular users:
If you forgot to set the directory in Step 5, you can then use
sudo mv <extracted_folder> /opt/intel (for root users or administrators), or
mv <extracted_folder> /home/<USER>/intel/ (for regular users) to set that.
For simplicity, it is useful to create a symbolink link:
ln -s /home/<USER>/intel/<extracted_folder> /home/<USER>/intel/openvino_2022
If such link already exists, remove the previous link with
/home/<USER>/intel/openvino_<version>/ will be referred as the standard OpenVINO
<INSTALL_DIR> in this document.
The core components are now installed. Continue to the next section to install components.
Step 2: Configure the Environment¶
You must update several environment variables before you can compile and run OpenVINO™ applications. Set environment variables as follows:
If you have more than one OpenVINO™ version on your machine, you can easily switch its version by sourcing
setupvars.sh of your choice.
You can also run this script every time when you start new terminal session. Open
~/.bashrc in your favorite editor, and add
source <INSTALL_DIR>/setupvars.sh. Next time when you open a terminal, you will see
[setupvars.sh] OpenVINO™ environment initialized. Changing
.bashrc is not recommended when you have many OpenVINO™ versions on your machine and want to switch among them, as each may require different setup.
The environment variables are set. Next, you can download some additional tools.
Step 3 (Optional): Install Additional Components¶
Since the OpenVINO™ 2022.1 release, the following development tools: Model Optimizer, Post-Training Optimization Tool, Model Downloader and other Open Model Zoo tools, Accuracy Checker, and Annotation Converter can only be installed via PyPI. See Install OpenVINO™ Development Tools for detailed steps.
OpenCV is necessary to run demos from Open Model Zoo (OMZ). Some OpenVINO samples can also extend their capabilities when compiled with OpenCV as a dependency. To install OpenCV for OpenVINO, see the instructions on Github.
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.
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.
While working with either HDDL or NCS, choose one of them as they cannot run simultaneously on the same machine.
To enable the toolkit components to use Intel® Gaussian & Neural Accelerator (GNA) on your system, follow the steps in GNA Setup Guide.
Now you are ready to try out the toolkit.
Start with some Python tutorials:
To start with C++ samples, see Build Sample Applications on Linux first, and then you can try the following samples:
Uninstalling the Intel® Distribution of OpenVINO™ Toolkit¶
To uninstall the toolkit, follow the steps on the Uninstalling page.
Converting models for use with OpenVINO™: Model Optimizer User Guide
Writing your own OpenVINO™ applications: OpenVINO™ Runtime User Guide
Sample applications: OpenVINO™ Toolkit Samples Overview
Pre-trained deep learning models: Overview of OpenVINO™ Toolkit Pre-Trained Models
IoT libraries and code samples in the GitHUB repository: Intel® IoT Developer Kit