microsoft/EdgeML

This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.

51
/ 100
Established

This library helps embedded systems engineers and IoT device developers create machine learning models that can run directly on small, resource-constrained hardware. It takes your raw sensor data or time-series inputs and produces highly efficient, tiny models for tasks like classification or anomaly detection. These models can then make real-time predictions offline without needing to connect to the cloud.

1,664 stars. No commits in the last 6 months.

Use this if you need to deploy AI capabilities to Internet of Things (IoT) devices, microcontrollers, or sensors that have very limited memory, processing power, and battery life.

Not ideal if your application runs on cloud servers or powerful devices, where model size and inference speed are not critical constraints.

IoT embedded-systems sensor-data-analytics real-time-inference edge-computing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,664

Forks

386

Language

C++

License

Last pushed

May 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/EdgeML"

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