Quantco/spox
Pythonic framework for building ONNX graphs
This tool helps machine learning engineers and researchers precisely define and construct ONNX (Open Neural Network Exchange) models using Python. It takes your desired model logic, expressed in Python, and outputs a validated ONNX model file. This is particularly useful for those who need to convert or create models that adhere to the ONNX standard for deployment or interoperability across different machine learning frameworks.
Available on PyPI.
Use this if you need to build or convert machine learning models into the ONNX format with strong type checking and clear error messages during development.
Not ideal if you primarily work within a single machine learning framework like PyTorch or TensorFlow and don't require ONNX model conversion or construction.
Stars
94
Forks
8
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Quantco/spox"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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