yet-another-onnx-builder documentation

yet-another-onnx-builder on GitHub

yet-another-onnx-builder (yobx) proposes a unique API to convert machine learning models to ONNX format and manipulating ONNX graphs programmatically. It can export from many libraries:

standard machine learning

category_encoders	scikit-learn Export to ONNX
imbalanced-learn	scikit-learn Export to ONNX
lightgbm	scikit-learn Export to ONNX
scikit-learn	scikit-learn Export to ONNX
scikit-survival	scikit-learn Export to ONNX
xgboost	scikit-learn Export to ONNX

data manipulations

This is work in progress. Many packages produce SQL queries. It starts by converting a SQL query into ONNX.

• SQL-to-ONNX Converter Design

deep learning

jax in progress	Converting a JAX function to ONNX
tensorflow	TensorFlow / JAX Export to ONNX
torch	Torch Export to ONNX
TFLite / LiteRT	LiteRT / TFLite Export to ONNX

It also provides:

• A graph builder API for constructing and optimizing ONNX graphs, with built-in shape inference and a pattern-based graph optimizer.

• Converters for scikit-learn estimators and pipelines (yobx.sklearn).

• Utilities for PyTorch export, including model patching and input flattening (yobx.torch).

• A symbolic shape expression system for dynamic shape handling at export time.

• A translation tool that converts ONNX graphs back to executable Python code.

• Optimization functions to make the model more efficient.

• It supports multiple opsets and multiple domains.

• It allows the user to directly onnx model with spox or onnxscript/ir-py.

Its unique API:

# the model is called
expected = model(*args, **kwargs)
onnx_model = to_onnx(model, args, kwargs, dynamic_shapes, **options)

• API
• Converters
• Core
• Galleries
• Command Lines
• Installation
• Getting Started
• Miscellaneous

Indices and tables

• Index

• Module Index

• Search Page

Older versions

• 0.1.0