mshr-h/onnx2fx
Turn ONNX models into inspectable, transformable, and trainable PyTorch FX GraphModules
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.
Stars
10
Forks
—
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX