ML-TN-001 - AI at the edge: comparison of different embedded platforms - Part 1

Info Box Applies to Machine Learning

Work in progress

History

Version	Date	Notes
1.0.0	September 2020	First public release

Introduction

This Technical Note (TN for short) is the first one of a series illustrating how machine learning-based inference applications perform across different embedded platforms, which are eligible for building intelligent edge devices.

The idea is to develop one or more applications with the help of well-known open-source frameworks/libraries and to deploy them on such platforms to compare performances, resource utilization, development flow, etc.

Test application #1: fruit classifier

This application implements a classifier like the one described here. There is one notable difference, however. In this case, the model was created from scratch using TBD.

Articles in this series

The other articles in this series are:

• Part 2: testing on Mito8M SoM (NXP i.MX8M)
• Part 3: testing on Xilinx Zynq UltraScale+ MPSoC ZCU104 Evaluation Kit)
• Part 4: testing on NXP i.MX8M Plus EVK)