"A scikit-learn for microcontrollers".
Project: https://github.com/emlearn/emlearn
Video. Will be published by TinyML Foundation. Later in 2024.
emlearn is an open-source Python library that allows converting scikit-learn and Keras models to efficient C code. The goal of the project is to make it easy to deploy efficient models to any microcontroller with a C99 compiler, while keeping Python-based workflow that is familiar to Machine Learning Engineers. The project was first released in 2018, predating many other TinyML libraries. Over the years the library has been used in a wide range of applications, from detection of vechicles in acoustic sensor nodes, to tracking welbeing of grazing cows using accelerometers, to hand gesture recognition based on sEMG data, to real-time malware detection in Android devices. In this presentation we will showcase a selection usecases and discuss their impact. We will also cover some of the latest improvements, such as optimized decision tree ensembles, and native support for MicroPython.