leleonardzhang/Capuchin

A framework and model generator for Neural Network inferences on MSP430

36
/ 100
Emerging

This project helps embedded systems engineers and researchers deploy trained neural network models onto resource-constrained TI MSP430FR5994 microcontrollers. It takes a pre-trained TensorFlow Keras model as input and outputs a C header file containing the model's configuration. This header file can then be compiled and run on the MSP430 to perform inferences.

No commits in the last 6 months.

Use this if you need to run pre-trained neural network models on 16-bit microcontrollers like the TI MSP430FR5994 for edge inference applications.

Not ideal if you are working with microcontrollers other than the MSP430FR5994 or if your neural network models utilize advanced layers not listed as supported.

embedded-systems microcontroller-programming edge-ai neural-network-deployment firmware-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

11

Forks

5

Language

C

License

Apache-2.0

Last pushed

May 25, 2022

Commits (30d)

0

Get this data via API

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

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