mit-han-lab/mcunet

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

57
/ 100
Established

This project helps embedded systems engineers and IoT device developers deploy complex machine learning models, like those for image classification or person detection, onto tiny, low-power microcontrollers. It takes your trained deep learning models and optimizes them to run efficiently, delivering faster inference and significantly reduced memory usage on resource-constrained IoT devices. This allows smart features to run directly on devices without needing to connect to the cloud.

664 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to run sophisticated AI capabilities, such as real-time image analysis, directly on microcontrollers with extremely limited memory and processing power, making your IoT devices smarter and more autonomous.

Not ideal if your application runs on devices with ample memory and computational resources, such as smartphones, personal computers, or cloud servers, as its primary benefit is extreme resource optimization.

IoT embedded-AI edge-computing microcontroller-development on-device-machine-learning
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

664

Forks

105

Language

Python

License

MIT

Last pushed

Mar 29, 2024

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mit-han-lab/mcunet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.