Date: Wednesday, May 18 (Main Conference Day 2)
Start Time: 2:05 pm
End Time: 2:35 pm
Development of vision AI applications for the edge presents complex challenges beyond model inference, often requiring end-to-end acceleration and optimization, spanning I/O to post-processing. Today, for organizations to overcome these challenges and launch successful vision AI products, they need expertise across many domains: machine learning, computer vision, video compression, embedded software and I/O interfaces. Learn how the NVIDIA DeepStream SDK helps organizations overcome these challenges and accelerate their time to market by abstracting away the necessary low-level details, enabling them to focus on the development of the unique functionality of the end application. In this tutorial session, users will learn how to create, test and deploy a fully optimized and accelerated vision AI application on a Jetson device in minutes using Graph Composer, a low-code design tool for DeepStream.