emlearn-micropython

Micropython integration for the emlearn Machine Learning library for microcontrollers.

It enables MicroPython applications to run efficient Machine Learning models on microcontroller, without having to touch any C code.

scikit-learn for Microcontrollers

This is a TinyML library, particularly well suited for low-compexity and low-power classification tasks. It can be combined with feature preprocessing, including neural networks to address more complex tasks.

Status

Minimally useful

• Has been tested on armv6m (RP2040), xtensawin (ESP32) and x64 (Unix port)
• Pre-built modules are available for the most common architectures/devices

Features

• Classification with RandomForest/DecisionTree models
• Classification and on-device learning with K-Nearest Neighbors (KNN)
• Installable as a MicroPython native module. No rebuild/flashing needed
• Models can be loaded at runtime from a .CSV file in disk/flash
• Highly efficient. Inference times down to 100 microseconds, RAM usage <2 kB, FLASH usage <2 kB

Prerequisites

Minimally you will need

• Python 3.10+ on host
• MicroPython 1.22+ running onto your device

Download repository

Download the repository with examples etc

git clone https://github.com/emlearn/emlearn-micropython

Installing from a release

Find architecture

Identify which CPU architecture your device uses. You need to specify ARCH to install the correct module version.

Download release files

Download from releases.

Install on device

Copy the .mpy file for the correct ARCH to your device.

mpremote cp emltrees.mpy :emltrees.mpy
mpremote cp emlneighbors.mpy :emlneighbors.mpy

NOTE: If there is no ready-made build for your device/architecture, then you will need to build the .mpy module yourself.

Usage

NOTE: Make sure to install the module first (see above)

Train a model with scikit-learn

pip install emlearn scikit-learn
python examples/xor_trees/xor_train.py

Copy model file to device

mpremote cp xor_model.csv :xor_model.csv

Run program that uses the model

mpremote run examples/xor_run.py

Benchmarks

UCI handwriting digits

UCI ML hand-written digits datasets dataset from sklearn.datasets.load_digits. 8x8 image, 64 features. Values are 4-bit integers (16 levels). 10 classes.

Running with a very simple RandomForest, 7 trees. Reaches approx 86% accuracy. Tested on Raspberry PI Pico, with RP2040 microcontroller (ARM Cortex M0 @ 133 MHz).

NOTE: over half of the time for emlearn case, is spent on converting the Python lists of integers into a float array. Removing that bottleneck would speed up things considerably.

Developing locally

Prerequisites

These come in addition to the prequisites described above.

Make sure you have the dependencies needed to build for your platform. See MicroPython: Building native modules.

We assume that micropython is installed in the same place as this repository. If using another location, adjust MPY_DIR accordingly.

You should be using the latest MicroPython 1.22 (or newer).

Build

Build the .mpy native module

make dist ARCH=armv6m MPY_DIR=../micropython

Install it on device

mpremote cp dist/armv6m*/emltrees.mpy :emltrees.mpy

Run tests

To build and run tests on host

make check

Citations

If you use emlearn-micropython in an academic work, please reference it using:

@misc{emlearn_micropython,
  author       = {Jon Nordby},
  title        = {{emlearn-micropython: Efficient Machine Learning engine for MicroPython}},
  month        = aug,
  year         = 2023,
  doi          = {10.5281/zenodo.8212731},
  url          = {https://doi.org/10.5281/zenodo.8212731}
}