Install OpenVINO™ Runtime on Windows from an Archive File

With the OpenVINO™ 2022.3 release, you can download and use archive files to install OpenVINO Runtime. The archive files contain pre-built binaries and library files needed for OpenVINO Runtime, as well as code samples.

Installing OpenVINO Runtime from archive files is recommended for C++ developers. If you are working with Python, the PyPI package has everything needed for Python development and deployment on CPU and GPUs. See the Install OpenVINO from PyPI page for instructions on how to install OpenVINO Runtime for Python using PyPI.

Note

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.

See the Release Notes for more information on updates in the latest release.

System Requirements

Full requirement listing is available in:

Processor graphics are not included in all processors. See Product Specifications for information about your processor.

Note

To install Microsoft Visual Studio 2019, follow the Microsoft Visual Studio installation guide. You can choose to download the Community version. During installation in the Workloads tab, choose Desktop development with C++.

Note

You can either use cmake<version>.msi which is the installation wizard or cmake<version>.zip where you have to go into the bin folder and then manually add the path to environmental variables.

Important

When installing Python, make sure you click the option Add Python 3.x to PATH to add Python to your PATH environment variable.

Installing OpenVINO Runtime

Step 1: Download and Install OpenVINO Core Components

  1. Create an Intel folder in the C:\Program Files (x86)\ directory. Skip this step if the folder already exists.

    You can also do this via command-lines. Open a new command prompt window as administrator by right-clicking Command Prompt from the Start menu and select Run as administrator, and then run the following command:

    mkdir "C:\Program Files (x86)\Intel"

    Note

    C:\Program Files (x86)\Intel is the recommended folder. You may also use a different path if desired or if you don’t have administrator privileges on your computer.

  2. Download the OpenVINO Runtime archive file for Windows to your local Downloads folder.

    If you prefer using command-lines, run the following commands in the command prompt window you opened:

    cd <user_home>/Downloads
    curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2022.3/windows/w_openvino_toolkit_windows_2022.3.0.9052.9752fafe8eb_x86_64.zip --output openvino_2022.3.0.zip

    Note

    A .sha256 file is provided together with the archive file to validate your download process. To do that, download the .sha256 file from the same repository and run CertUtil -hashfile openvino_2022.3.0.zip SHA256. Compare the returned value in the output with what’s in the .sha256 file: if the values are the same, you have downloaded the correct file successfully; if not, create a Support ticket here.

  3. Use your favorite tool to extract the archive file, rename the extracted folder, and move it to the C:\Program Files (x86)\Intel directory.

    To do this step using command-lines, run the following commands in the command prompt window you opened:

    tar -xf openvino_2022.3.0.zip
    ren w_openvino_toolkit_windows_2022.3.0.9052.9752fafe8eb_x86_64 openvino_2022.3.0
    move openvino_2022.3.0 "C:\Program Files (x86)\Intel"
  4. For simplicity, it is useful to create a symbolic link. Open a command prompt window as administrator (see Step 1 for how to do this) and run the following commands:

    cd C:\Program Files (x86)\Intel
    mklink /D openvino_2022 openvino_2022.3.0

    Note

    If you have already installed a previous release of OpenVINO 2022, a symbolic link to the openvino_2022 folder may already exist. If you want to override it, nagivate to the C:\Program Files (x86)\Intel folder and delete the existing linked folder before running the mklink command.

Congratulations, you finished the installation! The C:\Program Files (x86)\Intel\openvino_2022 folder now contains the core components for OpenVINO. If you used a different path in Step 1, you will find the openvino_2022 folder there. The path to the openvino_2022 directory is also referred as <INSTALL_DIR> throughout the OpenVINO documentation.

Step 2: Configure the Environment

You must update several environment variables before you can compile and run OpenVINO™ applications. Open the Command Prompt, and run the setupvars.bat batch file to temporarily set your environment variables. If your <INSTALL_DIR> is not C:\Program Files (x86)\Intel\openvino_2022, use the correct directory instead.

"C:\Program Files (x86)\Intel\openvino_2022\setupvars.bat"

Important : The above command must be re-run every time a new Command Prompt window is opened.

Note

If you see an error indicating Python is not installed, Python may not be added to the PATH environment variable (as described here). Check your system environment variables, and add Python if necessary.

The environment variables are set. Continue to the next section if you want to download any additional components.

Step 3 (Optional): Install Additional Components

OpenVINO Development Tools is a set of utilities for working with OpenVINO and OpenVINO models. It provides tools like Model Optimizer, Benchmark Tool, Post-Training Optimization Tool, and Open Model Zoo Downloader. If you install OpenVINO Runtime using archive files, OpenVINO Development Tools must be installed separately.

See the Install OpenVINO Development Tools page for step-by-step installation instructions.

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

OpenVINO Runtime has a plugin architecture that enables you to run inference on multiple devices without rewriting your code. Supported devices include integrated GPUs, discrete GPUs, NCS2, VPUs, and GNAs. See the instructions below to set up OpenVINO on these devices.

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

To install and configure your Intel® Vision Accelerator Design with Intel® Movidius™ VPUs, see the VPU Configuration Guide.

No additional configurations are needed.

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

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 Python Quick Start Example to estimate depth in a scene using an OpenVINO monodepth model in a Jupyter Notebook inside your web browser.

https://user-images.githubusercontent.com/15709723/127752390-f6aa371f-31b5-4846-84b9-18dd4f662406.gif

Visit the Tutorials page for more Jupyter Notebooks to get you started with OpenVINO, such as:

Try the C++ Quick Start Example for step-by-step instructions on building and running a basic image classification C++ application.

https://user-images.githubusercontent.com/36741649/127170593-86976dc3-e5e4-40be-b0a6-206379cd7df5.jpg

Visit the Samples page for other C++ example applications to get you started with OpenVINO, such as:

Uninstalling OpenVINO Runtime

To uninstall OpenVINO, follow the steps on the Uninstalling page.

Additional Resources

Additional Resources

  • ref

    Troubleshooting Guide for OpenVINO Installation & Configuration <troubleshooting guide for install>

  • Converting models for use with OpenVINO™: :ref: Model Optimizer Developer Guide <deep learning model optimizer>

  • Writing your own OpenVINO™ applications: :ref: OpenVINO™ Runtime User Guide <deep learning openvino runtime>

  • Sample applications: :ref: OpenVINO™ Toolkit Samples Overview <code samples>

  • Pre-trained deep learning models: :ref: Overview of OpenVINO™ Toolkit Pre-Trained Models <model zoo>

  • IoT libraries and code samples in the GitHUB repository: Intel® IoT Developer Kit _