TinyML Benchmark: Executing Fully Connected Neural Networks on Commodity Microcontrollers
Bharath Sudharsan, Simone Salerno, Duc-Duy Nguyen, Muhammad Yahya, Abdul Wahid, Piyush Yadav, John G. Breslin, Muhammad Intizar Ali
Abstract
Recent advancements in the field of ultra-low-power machine learning (TinyML) promises to unlock an entirely new class of edge applications. However, continued progress is restrained by the lack of benchmarking Machine Learning (ML) models on TinyML hardware, which is fundamental to this field reaching maturity. In this paper, we designed 3 types of fully connected Neural Networks (NNs), trained each NN using 10 datasets (produces 30 NNs), and present the benchmark by reporting the onboard model performance on 7 popular MCU-boards (similar boards are used to design TinyML hardware). We open-sourced and made the complete benchmark results freely available online <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> to enable the TinyML community researchers and developers to systematically compare, evaluate, and improve various aspects during the design phase of ML-powered IoT hardware. 1Trained TFLite models, complete benchmark results, and more details on chosen MCU boards, datasets, NNs are available at https://github.com/bharathsudharsan/TinyML-Benchmark-NNs-on-MCUs