TinyML Platforms Benchmarking

Recent advances in state-of-the-art ultra-low power embedded devices for machine learning (ML) have permitted a new class of products whose key features enable ML capabilities on microcontrollers with less than 1 mW consumption (TinyML). TinyML provides unique solution by aggregating and analyzing data at the edge low-power devices. However, we only recently been able to run microcontrollers, field is still its infancy, which means that hardware, software, research are changing extremely rapidly. Consequently, many frameworks developed different platforms facilitate deployment models standardize process. Therefore, this paper, focus benchmarking two popular frameworks: Tensorflow Lite Micro (TFLM) Arduino Nano BLE CUBE AI STM32-NucleoF401RE provide standardized framework selection criterion specific applications.