Earlier this year, Amazon, Facebook, and Microsoft partnered to create the Open Neural Network Exchange (ONNX)—an open format to represent deep learning models. This specification and set of tools, supported by a community of partners, is the first step toward an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX’s ecosystem includes converters from and to popular deep learning frameworks as well as bindings to hardware-optimized libraries. Sarah Bird explains in detail how the ONNX framework can help you take AI from research to reality as quickly as possible. Join in to learn how to overcome the challenges of transferring models from one framework to another using ONNX.
Sarah Bird is a technical program manager at Facebook AI Research and its Applied Machine Learning Lab, where she leads strategic projects at the intersection of research and product.
©2018, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com