AWS Machine Learning Blog

Announcing the Availability of ONNX 1.0

Today, Amazon Web Services (AWS), Facebook and Microsoft are pleased to announce that the Open Neural Network Exchange (ONNX) format is production ready.

ONNX is an open standard format for deep learning models that enables interoperability between deep learning frameworks such as Apache MXNet, Caffe2, Microsoft Cognitive Toolkit, and PyTorch. ONNX 1.0 enables users to move deep learning models between frameworks, making it easier to put them into production. For example, developers can build sophisticated computer vision models using frameworks such as PyTorch and run them for inference using Microsoft Cognitive Toolkit or Apache MXNet.

We are excited to see the growth and momentum of community support and involvement since the initial release of ONNX in September. Numerous hardware partners including Qualcomm, Huawei, and Intel announced support of the ONNX format for their hardware platforms, making it easier for users to run models on different hardware platforms. We are grateful to the community of contributors who committed code and support for new features.

We will continue to work with our ONNX partners and the community to evolve ONNX, ensuring that developers have access to the latest research to integrate state of-the-art models into production applications.

Related Announcements

About the Author

Sukwon Kim is a Senior Product Manager for AWS Deep Learning. He works on products that make it easier for customers to use deep learning engines with a specific focus on the open source Apache MXNet engine. In his spare time, he enjoys hiking and traveling.