s1ddok/Sardonyx

Convert your ONNX models into Swift for TensorFlow or Metal Performance Shaders (WIP)

22
/ 100
Experimental

This tool helps machine learning engineers and researchers deploy deep learning models trained in frameworks like PyTorch or TensorFlow into Swift applications. It takes an ONNX model file as input and generates Swift code along with a data blob. The output can then be integrated into Swift for TensorFlow or Metal Performance Shaders projects, simplifying the deployment of trained models.

No commits in the last 6 months.

Use this if you need to integrate existing ONNX-compatible deep learning models into Swift applications for iOS, macOS, or other Apple platforms, particularly for tasks like image classification.

Not ideal if your ONNX model uses layers not yet supported for Swift for TensorFlow or Metal Performance Shaders, or if you require deployment to non-Apple platforms.

machine-learning-deployment mobile-ml swift-development neural-network-conversion model-porting
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

25

Forks

2

Language

Swift

License

Last pushed

Apr 21, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ai-coding/s1ddok/Sardonyx"

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