microsoft/EdgeML
This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.
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.
Stars
1,664
Forks
386
Language
C++
License
—
Category
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.
Related frameworks
emlearn/emlearn
Machine Learning inference engine for Microcontrollers and Embedded devices
analogdevicesinc/ai8x-training
Model Training for ADI's MAX78000 and MAX78002 Edge AI Devices
DT42/BerryNet
Deep learning gateway on Raspberry Pi and other edge devices
eclypse-org/eclypse
An Edge-Cloud python platform for simulated (and emulated) runtime environments
SummerGift/EmbeddedSystem
:books: 计算机体系架构、嵌入式系统基础与主流编程语言相关内容总结