microsoft/onnxconverter-common

Common utilities for ONNX converters

What it solves

It provides a shared set of utilities and functions that simplify the process of converting AI models from various frameworks to the ONNX format. It specifically addresses the problem of converting models that use a mix of different frameworks (e.g., a scikit-learn pipeline containing an XGBoost model).

How it works

The package acts as a common library of helper functions that different framework-specific converters can use to ensure consistency and interoperability between them during the model conversion process.

Who it’s for

Developers and engineers who are building or maintaining converters that translate AI models from different frameworks into ONNX.

Highlights

  • Shared utilities for AI framework converters
  • Support for mixed-framework model conversion
  • MIT License

Related

  • Project
    onnx/onnxmltools

    A toolkit for converting machine learning models from various frameworks like TensorFlow, scikit-learn, and XGBoost into the ONNX format for cross-platform deployment.

  • Project
    onnx/models

    A curated collection of pre-trained, state-of-the-art machine learning models in the ONNX format, enabling cross-framework compatibility and deployment.

  • Project
    onnx/sklearn-onnx

    A library that converts scikit-learn models to the ONNX format, enabling high-performance inference using ONNX Runtime.

  • Project
    Talmaj/onnx2pytorch

    A library that transforms ONNX models into PyTorch models, allowing users to utilize PyTorch's backend and neural network manipulation tools.

  • Project
    onnx/onnx

    ONNX is an open, framework‑agnostic model format and reference implementation that lets you move AI models between tools and runtimes. Install via `pip install onnx`, use the Python API to build or load a graph, then run inference with any ONNX‑compatible engine.