|ONNX Models to be Runnable Natively on 100s of Millions of Windows Devices|
March 7, 2018 by Cortana Intelligence and ML Blog Team // 0 Comments
This post was authored by Eric Boyd, CVP, AI Data & Infrastructure.
Today Microsoft is announcing the next major update to Windows will include the ability to run Open Neural Network Exchange (ONNX) models natively with hardware acceleration. This brings 100s of millions of Windows devices, ranging from IoT edge devices to HoloLens to 2-in-1s and desktop PCs, into the ONNX ecosystem. Data scientists and developers creating AI models will be able to deploy their innovations to this large user base. And every developer building apps on Windows 10 will be able to use AI models to deliver more powerful and engaging experiences.
ONNX is an open source model representation for interoperability and innovation in the AI ecosystem. We helped startONNX last September, added support from many other companies, and launched ONNX 1.0 in December with Facebook and Amazon Web Services. With the ONNX format, developers can choose the right framework for their task, framework authors can focus on innovative enhancements and hardware vendors can streamline optimizations.
Thanks to ONNX-ML, Windows supports both classic machine learning and deep learning, enabling a spectrum of AI models and scenarios. Developers can obtain ONNX models to include in their apps in several ways:
You can learn more about how to integrate ONNX models into Windows apps here.
- Create and train ONNX models using any of the frameworks that currently support generating ONNX models including Caffe2, Chainer, PyTorch, and Microsoft Cognitive Toolkit (CNTK).
- Convert models from various sources including SciKit-Learn and CoreML into ONNX models by using ONNXML tools.
- Obtain pre-trained ONNX models from the growing ONNX model zoo. (If you create an ONNX model, we encourage you to contribute it here to share with the community!)
At Microsoft we believe bringing AI advances to all developers, on any platform, using any language, with an open AI ecosystem, will help ensure AI is more accessible and valuable to all. With ONNX, the new AI capabilities in Windows, and Azure AI services, infrastructure and tools such as Azure Machine Learning and Visual Studio Tools for AI, developers and data scientists will be able to deliver new and exciting AI innovations faster.
To learn more about ONNX and participate in the effort, visit onnx.ai. You can also get updates via Facebook and @onnxai on Twitter.