It is a toolkit provided by Intel to facilitate faster inference of deep learning models. It helps developers to create cost-effective and robust computer vision applications. It enables deep learning inference at the edge and supports heterogeneous execution across computer vision accelerators — CPU, GPU, Intel® Movidius™ Neural Compute Stick, and FPGA.

The OpenVINO™ Toolkit’s name comes from “Open Visual Inferencing and Neural Network Optimization”. It is largely focused around optimizing neural network inference and is open source.

OpenVINO™ Toolkit

1. Enables deep learning inference on CNN-based edge devices
2. Supports heterogeneous execution across an Intel® CPU (Central Processing Unit), Intel® Integrated Graphics Processing Unit (IGPU), Intel® FPGA (Field Programmable Gate Array), Intel® Neural Compute Stick 2 (NCS2) and Intel® Vision Accelerator Design with Intel® Movidius™ VPUs
3. With the use of an easy-to-use library of computer vision functions and preoptimized kernels, it speeds time-to-market
4. Includes optimized calls for computer vision standards, including OpenCV* and OpenCL™

To learn more, visit.