Most AI algorithms created for edge applications are initially developed on workstations. Developers then often struggle to get these workloads running on edge devices. This holds true for a wide range of applications, from IoT to automotive to XR to mobile to compute.
The Qualcomm AI Stack streamlines the path from initial algorithm development to edge deployment. The Qualcomm AI Stack makes it easy to retarget algorithms to edge hardware by supporting frameworks and data types that AI developers are familiar with. And it provides a set of tools that empower developers to extract the best performance and energy efficiency from their target hardware.
In this session, we will walk you through the steps of building a sample Android application for AI-based image super resolution using the Qualcomm AI Stack. Through this sample app, we’ll show how applications built with AI runtimes utilize hardware optimizations for Qualcomm devices. We will also share tips and tricks on quantization, explore how model accuracy affects performance and power, and outline the tooling that helps developers successfully implement new AI capabilities in their products.
Santa Clara Convention Center – Room 209/210
Coffee and pastries will be provided
Follow us on Twitter and LinkedIn.
Open for submissions! If you’re a start-up doing something cool with computer vision or visual AI, submit your entry today—for free! (Not at a computer vision or visual AI start-up but know one? Nominate them and you could win free Summit passes!) https://hubs.ly/Q01ws0cX0
Last chance! Don’t miss your chance to win year-round promotion of your company by the Alliance by winning an Edge AI and Vision Product of the Year Award. Submit your entry by December 31! https://hubs.ly/Q01svnzB0