Register today for upcoming Arm Tech Talks: https://www.arm.com/techtalks

Get ready for another one of our Arm Tech Talks! Every fortnight, we discuss and explore some of the latest trends, technologies and best practices in the world of AI, featuring partners from the AI Ecosystem as well as speakers across Arm.

00:00 Welcome & intros
03:32 Hear about Alif and the Ensemble Platform
10:17 Emza introduction
10:48 From Model to deployment
26:16 Demo of Face Detection on Alif Ensemble Platform
30:10 Resources
31:15 Q&A
52:47 Let’s see that demo one more time!

With the introduction of the Cortex-M55 and the Ethos-U55 micro NPU, object detection at the tiny edge is now becoming a reality. In this session, you will learn how to run object detection models on the very first silicon that uses the Ethos-U55 – the Ensemble product from Alif Semiconductor.

Alif representatives will present an overview of the Ensemble product line and will provide details on its evaluation kit. In addition, Arm AI Ecosystem Partner Emza Visual Sense will walk through the creation of a face detection model, from model training to running the model on the Arm ML Embedded Evaluation Kit to porting the model to Alif silicon.

Emza will provide details on model training and data that improves detection performance for low-resolution monochrome images. We will walk through an object detection example (available in open source) that is using Arm’s ML Eval Kit for Ethos-U55, then show the migration process to real silicon. How fast it can run? You’ll be surprised!

If you enjoyed this video, please subscribe to our channel and make sure to add us on Twitter so you can get a lot more content like this delivered straight to your feed!
Tweets by ArmSoftwareDev

source