emlearn
emlearn · 774 GitHub stars
Converts scikit-learn and Keras models into portable C code for inference on microcontrollers.
- Follows branch
master: eachwest updatewill get its latest commits. To stay on one version, it is recommended to use a release tag.
Install
# From the workspace root
curl -fsSL https://kartben.github.io/windrose/m/emlearn.yaml \
-o zephyr/submanifests/emlearn.yaml
west update emlearn
# From the workspace root
Invoke-WebRequest https://kartben.github.io/windrose/m/emlearn.yaml `
-OutFile zephyr/submanifests/emlearn.yaml
west update emlearn
west.yml
- name: emlearn url: https://github.com/emlearn/emlearn revision: master path: modules/lib/emlearn
Add to projects in your west.yml, then run west update emlearn.
Details
- Revision
- master
- License
- MIT
- Maintainers
- @emlearn
- Last commit
- 3 days ago
About
emlearn is an open source library for deploying machine learning models on micro-controllers and embedded systems. It provides portable C code generation from models trained with scikit-learn or Keras.
A Python library allows converting complex machine learning models to a minimal C code representation, which enables running ML inference on resource-constrained embedded devices.
emlearn is licensed under the MIT license.