U-TOE: Universal TinyML On-board Evaluation Toolkit for Low-Power IoT

TL;DR

U-TOE is an open-source, comprehensive toolkit designed to evaluate the performance of machine learning models on low-power IoT devices, facilitating research and development in TinyML and edge computing.

Contribution

It introduces U-TOE, a universal, all-in-one toolkit that combines model transpilation, performance measurement, and remote testing for low-power IoT hardware.

Findings

Demonstrated evaluation of models on various IoT boards

Enabled reproducible and customizable performance comparisons

Facilitated rapid assessment of TinyML feasibility on microcontrollers

Abstract

Results from the TinyML community demonstrate that, it is possible to execute machine learning models directly on the terminals themselves, even if these are small microcontroller-based devices. However, to date, practitioners in the domain lack convenient all-in-one toolkits to help them evaluate the feasibility of executing arbitrary models on arbitrary low-power IoT hardware. To this effect, we present in this paper U-TOE, a universal toolkit we designed to facilitate the task of IoT designers and researchers, by combining functionalities from a low-power embedded OS, a generic model transpiler and compiler, an integrated performance measurement module, and an open-access remote IoT testbed. We provide an open source implementation of U-TOE and we demonstrate its use to experimentally evaluate the performance of various models, on a wide variety of low-power IoT boards, based on popular microcontroller architectures. U-TOE allows easily reproducible and customizable comparative evaluation experiments on a wide variety of IoT hardware all-at-once. The availability of a toolkit such as U-TOE is desirable to accelerate research combining Artificial Intelligence and IoT towards fully exploiting the potential of edge computing.