onnx/models

A collection of pre-trained, state-of-the-art models in the ONNX format

What it solves

It provides a centralized, curated collection of pre-trained, state-of-the-art machine learning models converted into the ONNX (Open Neural Network Exchange) format. This allows developers to use models across different frameworks, tools, runtimes, and compilers without being locked into the original training framework.

How it works

Models are sourced from prominent open-source repositories (such as timm, torchvision, and transformers) and exported to the ONNX format using the TurnkeyML toolchain. The repository uses Git LFS to handle large model files and includes a set of validated models across various domains to ensure accuracy.

Who it’s for

AI developers, researchers, and enthusiasts who want to deploy pre-trained models in an environment-agnostic way or use runtimes that support the ONNX standard.

Highlights

  • Broad Model Coverage: Includes models for Computer Vision (classification, detection, segmentation), NLP (comprehension, translation, modeling), Generative AI, and Graph Machine Learning.
  • Cross-Framework Compatibility: Enables models to be used with a variety of runtimes and compilers via the ONNX open standard.
  • Quantization Support: Provides INT8 models generated by the Intel® Neural Compressor for improved efficiency.
  • Validated Accuracy: Maintains a specific list of models that have been rigorously validated for accuracy.

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/sklearn-onnx

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

  • Project
    microsoft/onnxconverter-common

    A collection of common utilities and functions used by converters to translate AI models from various frameworks into the ONNX format.

  • 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.

  • Project
    PINTO0309/PINTO_model_zoo

    A comprehensive repository of AI models inter-converted and quantized for various frameworks like TensorFlow Lite, ONNX, and CoreML to simplify edge deployment.