Last month, Microsoft announced its collaboration with Facebook to introduce Open Neural Network Exchange (ONNX) format. ONNX brings interoperability to the AI framework ecosystem providing a definition of an extensible computation graph model, as well as definitions of built-in operators and standard data types. ONNX enables models to be trained in one framework and transferred to another for inference. ONNX models are currently supported in Caffe2, Cognitive Toolkit, and PyTorch. Since the announcement was made last month, this new format is gaining momentum across the industry. Microsoft yesterday announced that the following companies are announcing their support for the ONNX format.
Microsoft announced that they will be adopting the ONNX format widely inside the company and the preview support of ONNX in Cognitive Toolkit is now available for everyone to try out. They also announced that their FPGA-based deep learning platform Project Brainwave will support the ONNX format.
The ONNX code and documentation are available as open source on GitHub here.