"ML in a Minute" is our conversational series on answering machine learning questions. Have questions you want answered? Tweet at us.

What is OpenVINO (in 60 Seconds or Fewer)?

OpenVINO is a machine learning framework published by Intel to allow you to run machine learning models on their hardware. One of Intel's most popular hardware deployment options is a VPU, vision processing unit, and you need to be able to convert your model into OpenVINO in order to take advantage of the optimized processing [offered by a VPU].

Is There An Easy Way to Get a Model into OpenVINO?

Certainly. For example, Roboflow enables developers to deploy their edge, and OpenVINO is one of these supported frameworks. The Luxonis OpenCV AI Kit (OAK) is an example of one of these Intel-native hardware deployment options.

How to Train and Deploy Custom Models to Your OAK
In this blog, we’ll walk through the Roboflow custom model deployment process to the OAK and show just how seamless it can be.

Be sure to subscribe to our channel: https://bit.ly/rf-yt-sub

Liked this? Be sure to also check out the computer vision glossary.