mshr-h/onnx2fx

Turn ONNX models into inspectable, transformable, and trainable PyTorch FX GraphModules

37
/ 100
Emerging

This tool helps AI developers and researchers convert models from the ONNX format into PyTorch's FX GraphModule format. This allows for easier inspection, optimization, and fine-tuning of models like those used in PaddleOCR or large language models. The tool takes an ONNX model as input and outputs a PyTorch FX GraphModule that can be used within the PyTorch ecosystem.

Available on PyPI.

Use this if you need to integrate an existing ONNX model into a PyTorch workflow for advanced analysis, optimization, or to make it trainable within PyTorch.

Not ideal if you primarily work with other deep learning frameworks or do not need to perform low-level graph manipulations or training within the PyTorch ecosystem.

model-conversion deep-learning-research model-optimization AI-development machine-learning-engineering
Maintenance 10 / 25
Adoption 5 / 25
Maturity 22 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

Python

License

Apache-2.0

Last pushed

Mar 09, 2026

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mshr-h/onnx2fx"

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