mlomb/onnx2code

Convert ONNX models to plain C++ code (without dependencies)

18
/ 100
Experimental

This tool helps machine learning engineers or embedded systems developers convert trained ONNX (Open Neural Network Exchange) models into standalone C++ code. You provide an ONNX model file as input, and it generates C++ source files that can be compiled and run without any external dependencies. This is ideal for deploying AI models on resource-constrained devices or in environments where complex dependencies are undesirable.

No commits in the last 6 months.

Use this if you need to integrate a machine learning model into a C++ application with minimal dependencies, especially for embedded systems or high-performance computing.

Not ideal if your ONNX model uses advanced operations not listed as supported, requires quantized inference, or you are comfortable with existing ONNX runtime libraries.

embedded-machine-learning edge-computing model-deployment C++-development AI-inference
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

22

Forks

1

Language

Python

License

Last pushed

Mar 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mlomb/onnx2code"

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