microsoft/ml4f

ML model compiler for Cortex-M4F

38
/ 100
Emerging

This tool helps embedded systems developers deploy machine learning models more efficiently on resource-constrained microcontrollers. It takes a Keras sequential model, often in a TensorFlow.js format, and converts it into highly optimized ARM Thumb machine code. The output is a significantly faster model ready for use on Cortex-M4F (and better) microcontrollers, benefiting developers working on edge AI applications.

No commits in the last 6 months.

Use this if you are developing embedded systems with Cortex-M microcontrollers and need to run Keras machine learning models with significantly improved performance and reduced latency compared to standard interpreters.

Not ideal if you are working with non-Keras models, different microcontroller architectures, or if your application does not require extreme optimization of model inference speed on embedded devices.

embedded-development edge-ai microcontroller-programming machine-learning-deployment firmware-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

20

Forks

7

Language

TypeScript

License

MIT

Last pushed

May 27, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/ml4f"

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