Intel® Distribution of OpenVINO™ Toolkit

Your AI Inferencing Apps...Now Faster

Develop applications and solutions that uses deep learning intelligence with the Intel® Distribution of OpenVINO™ toolkit. Based on convolutional neural networks (CNN), the toolkit extends workloads across Intel® hardware (including accelerators) and maximizes performance.

Enables deep learning inference from edge to cloud
Accelerates AI workloads, including computer vision, audio, speech, language, and recommendation systems
Supports heterogeneous execution across Intel® architecture and AI accelerators—CPU, iGPU, Intel® Movidius™ Vision Processing Unit (VPU), FPGA, and Intel® Gaussian & Neural Accelerator (Intel® GNA)—using a common API

Speeds up time to market via a library of functions and preoptimized kernels
Includes optimized calls for OpenCV, OpenCL™ kernels, and other industry tools and libraries

Get Started

Discover the Capabilities

High Performance, Deep Learning

Accelerate deep neural network workloads across multiple platforms to achieve faster, more accurate results for AI inference.

Streamlined Development

Enable a streamlined, end-to-end development and deployment workflow.

Write Once, Deploy Anywhere

The Intel Distribution of OpenVINO toolkit supports heterogeneous execution across target environments with a high-level common API.

Intel offers a powerful portfolio of scalable hardware and software solutions, powered by the Intel Distribution of OpenVINO toolkit, to meet the various performance, power, and price requirements of any use case. See how the toolkit can boost your inference applications across multiple deep neural networks with high throughput and efficiency.

Performance Benchmarks

2021.2
2020.3.1 LTS

2021.2

What's New in the 2021.2 Release

Integrates the Deep Learning Workbench with the Intel® DevCloud for the Edge as a Beta release. Graphically analyze models using the Deep Learning Workbench on the Intel® DevCloud for the Edge (instead of a local machine only) to compare, visualize, and fine-tune a solution against multiple remote hardware configurations.
Introduces support for Red Hat* Enterprise Linux* 8.2
Implements loop support for increased control flow for dynamic models. This enables support for RNN-like dynamic models, such as YOLO* v3 using ONNX* (Open Neural Network Exchange).
Introduces per-channel quantization support in the Model Optimizer for models quantized with TensorFlow Quantization-Aware Training containing per-channel quantization for weights. This improves performance by model compression and latency reduction.
Pretrained models and support for public models to streamline development:
- Public Models: YOLO v4 (for object detection), AISpeech* (for speech recognition), and DeepLab v3 (for semantic segmentation)
- Pretrained Models: Human Pose Estimation (update), Formula Recognition Polynomial Handwritten (new), Machine Translation (update), Common Sign Language Recognition (new), and Text-to-Speech (new)
OpenVINO™ Security Add-on to allow control of models through secure packaging and model execution. Using kernel-based virtual machines (KVM) and Docker* containers, it is compatible with the OpenVINO™ model server for a scalable serving microservice. This new add-on enables packaging for flexible deployment and security.

Release Notes

Choose & Download

System Requirements

What You Can Do

Developers and enterprises are using the Intel Distribution of OpenVINO toolkit in industries, including industrial and manufacturing, healthcare, lab and life sciences, retail, safety and security, and emerging use cases. Learn how deep learning is changing industries.

Success Stories

2020.3.1 LTS

What's New in the 2020.3.1 LTS Release

Long-Term Support (LTS) is a new annual release type that provides longer-term maintenance and support with a focus on stability and compatibility. This allows you to deploy applications powered by the Intel Distribution of OpenVINO toolkit with more confidence. To get the latest features and leading performance, standard releases will continue to be made available three to four times a year.

Provides bug fixes for the previous 2020.3 LTS release. Read more about the support details.
Includes security and functionality bug fixes, and minor capability changes
Includes improved support for 11th generation Intel® Core™ Processor (formerly code named Tiger Lake), which includes Intel® Iris® Xe graphics and Intel DL Boost instructions.

Intel Distribution of OpenVINO toolkit 2020.3.X LTS releases will continue to support Intel® Vision Accelerator Design with an Intel® Arria® 10 FPGA and the Intel® Programmable Acceleration Card with Intel® Arria® 10 GX FPGA.

For questions about next-generation programmable deep-learning solutions based on FPGAs or to get the latest FPGA updates, talk to your sales representative or contact us.

Release Notes

LTS Documentation

Compressed Sensing + AI = Faster, High-Quality Medical Imaging

Medical imaging technologies, such as MRI and CT scanners, have benefited from the recent breakthroughs in AI to produce high-quality images faster than ever before.

Learn More