What is ONNX?

What is ONNX - Open Neural Network Exchange

ONNX is an open format to represent both deep learning and traditional models. With ONNX, AI developers can more easily move models between state-of-the-art tools and choose the combination that is best for them. ONNX is developed and supported by a community of partners such as Microsoft, Facebook and AWS.

ONNX is widely supported and can be found in many frameworks, tools, and hardware. Enabling interoperability between different frameworks and streamlining the path from research to production helps increase the speed of innovation in the AI community. ONNX helps to solve the challenge of hardware dependency related to AI models and enables deploying same AI models to several HW accelerated targets.


Watch channel 9 video that talks about ONNX

Get started with ONNX

Train an ONNX model using Azure Machine Learning.

Convert your model to ONNX

Convert to ONNX

  • Use ONNX Converter Image to convert other major model frameworks to ONNX. Supported frameworks are currently
    • CNTK, CoreML, Keras, scikit-learn, Tensorflow, PyTorch

Get started with examples

Here is a list of product examples using a ONNX and tested combination of hardware and AI model.

Want to publish your own example?
Send email to aiedge@microsoft.com