Overview

Intel® Distribution of OpenVINO™ toolkit is a comprehensive toolkit for developing applications and solutions based on deep learning tasks, such as: emulation of human vision, automatic speech recognition, natural language processing, recommendation systems, etc. It provides high-performance and rich deployment options, from edge to cloud. Some of its advantages are:

  • Enabling CNN-based deep learning inference on the edge.

  • Supporting various execution modes across Intel® technologies: Intel® CPU, Intel® Integrated Graphics, Intel® Neural Compute Stick 2, and Intel® Vision Accelerator Design with Intel® Movidius™ VPUs.

  • Speeding time-to-market via an easy-to-use library of computer vision functions and pre-optimized kernels.

Installation Options

Since the 2022.1 release, the OpenVINO installation package has been distributed in two parts: OpenVINO Runtime and OpenVINO Development Tools. See the following instructions to choose your installation process.

Decide What to Install

If you have already finished your model development and want to deploy your applications on various devices, install OpenVINO Runtime, which contains a set of libraries for easy inference integration with your products.

If you want to download models from Open Model Zoo, convert your own models to OpenVINO IR, or optimize and tune pre-trained deep learning models, install OpenVINO Development Tools, which provides the following tools:

  • Model Optimizer

  • Post-Training Optimization Tool

  • Benchmark Tool

  • Accuracy Checker and Annotation Converter

  • Model Downloader and other Open Model Zoo tools

Choose Your Installation Method

For Python developers, you can install OpenVINO from PyPI, which contains both OpenVINO Runtime and Development Tools, while requiring fewer steps.

For C++ developers, you may choose one of the following installation options for OpenVINO Runtime on your specific operating system:

Note

With the introduction of the 2022.1 release, the OpenVINO Development Tools can be installed only via PyPI. See Install OpenVINO Development Tools for detailed steps.

Source files are also available in the OpenVINO toolkit GitHub repository, so you can build your own package for the supported platforms, as described in OpenVINO Build Instructions.