U-TOE: Universal TinyML On-board Evaluation Toolkit for Low-Power IoT
This toolkit addresses a practical problem for IoT designers and researchers by providing an all-in-one solution for reproducible and customizable evaluation, potentially accelerating AI and IoT integration for edge computing.
The paper tackles the lack of convenient toolkits for evaluating machine learning models on low-power IoT hardware by presenting U-TOE, a universal toolkit that combines embedded OS, model transpiler, compiler, performance measurement, and remote testbed functionalities, demonstrating its use to experimentally evaluate various models on diverse IoT boards.
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.