Tools and Techniques for Optimizing DNNs on Arm-based Processors with Au-Zone’s DeepView ML Toolkit

Wednesday, May 22, 2:10 PM - 2:40 PM
Summit Track: 
Enabling Technologies
Exhibit Hall ET 2

In this presentation, we will describe methods and tools for developing, profiling and optimizing neural network solutions for deployment on Arm MCUs, CPUs and GPUs using Au-Zone’s DeepView ML Toolkit. We’ll introduce the need for optimization to enable efficient deployment of deep learning models, and will highlight the specific challenges of profiling and optimizing models for deployment in cost- and energy-constrained systems. We’ll show how Au-Zone’s DeepView tools can be used in conjunction with Arm’s Streamline tools to gain detailed insights into the performance of neural networks on ARM-based SoCs. Using a facial recognition solution as an example, we will explore how to evaluate, profile and optimize deep learning models on a Cortex-M7 MCU, a Cortex-A73/A53 big.LITTLE CPU and a MALI G-71 GPU.


Sébastien Taylor

Vision Technology Architect, Au-Zone

Mr. Taylor is the embedded Computer Vision technology lead at Au-Zone Technologies. Bringing over 18 years of experience in embedded software product development, his work focuses on the design, implementation and acceleration of traditional computer vision algorithms and Machine Learning deployments on embedded vision platforms. Sébastien has been leading an internal team developing Au-Zone’s graphical design tool DeepViewML Toolkit and embedded inference engine DeepViewRT.

See you at the Summit! May 18-21 in Santa Clara, California!