The Open Neural Network Exchange (ONNX) [] is an Open-source software, open-source artificial intelligence ecosystem of technology companies and research organizations that establish open standards for representing machine learning algorithms and software tools to promote innovation and collaboration in the AI sector. ONNX is available on

GitHub GitHub, Inc. () is an Internet hosting service for software development and version control using Git. It provides the distributed version control of Git plus access control, bug tracking, software feature requests, task management, continuous ...

History

ONNX was originally named Toffee and was developed by the

PyTorch PyTorch is a machine learning framework based on the Torch library, used for applications such as computer vision and natural language processing, originally developed by Meta AI and now part of the Linux Foundation umbrella. It is free and open ...

team at

Facebook Facebook is an online social media and social networking service owned by American company Meta Platforms. Founded in 2004 by Mark Zuckerberg with fellow Harvard College students and roommates Eduardo Saverin, Andrew McCollum, Dustin M ...

. In September 2017 it was renamed to ONNX and announced by Facebook and

Microsoft Microsoft Corporation is an American multinational technology corporation producing computer software, consumer electronics, personal computers, and related services headquartered at the Microsoft Redmond campus located in Redmond, Washing ...

. Later, IBM,

Huawei Huawei Technologies Co., Ltd. ( ; ) is a Chinese multinational technology corporation headquartered in Shenzhen, Guangdong, China. It designs, develops, produces and sells telecommunications equipment, consumer electronics and various smar ...

Intel Intel Corporation is an American multinational corporation and technology company headquartered in Santa Clara, California. It is the world's largest semiconductor chip manufacturer by revenue, and is one of the developers of the x86 seri ...

AMD Advanced Micro Devices, Inc. (AMD) is an American multinational semiconductor company based in Santa Clara, California, that develops computer processors and related technologies for business and consumer markets. While it initially manufactur ...

Arm In human anatomy, the arm refers to the upper limb in common usage, although academically the term specifically means the upper arm between the glenohumeral joint (shoulder joint) and the elbow joint. The distal part of the upper limb between th ...

and

Qualcomm Qualcomm () is an American multinational corporation headquartered in San Diego, California, and incorporated in Delaware. It creates semiconductors, software, and services related to wireless technology. It owns patents critical to the 5G, 4 ...

announced support for the initiative. In October 2017, Microsoft announced that it would add its Cognitive Toolkit and

Project Brainwave A project is any undertaking, carried out individually or collaboratively and possibly involving research or design, that is carefully planned to achieve a particular goal. An alternative view sees a project managerially as a sequence of even ...

platform to the initiative. In November 2019 ONNX was accepted as graduate project in Linux Foundation AI. In October 2020 Zetane Systems became a member of the ONNX ecosystem.

Intent

The initiative targets:

Framework interoperability

Allow developers to more easily move between frameworks, some of which may be more desirable for specific phases of the development process, such as fast training, network architecture flexibility or inferencing on mobile devices.

Shared optimization

Allow hardware vendors and others to improve the performance of

artificial neural network Artificial neural networks (ANNs), usually simply called neural networks (NNs) or neural nets, are computing systems inspired by the biological neural networks that constitute animal brains. An ANN is based on a collection of connected unit ...

s of multiple frameworks at once by targeting the ONNX representation.

ONNX provides definitions of an extensible computation graph model, built-in operators and standard

data type In computer science and computer programming, a data type (or simply type) is a set of possible values and a set of allowed operations on it. A data type tells the compiler or interpreter how the programmer intends to use the data. Most progra ...

s, focused on inferencing (evaluation). Each computation

dataflow In computing, dataflow is a broad concept, which has various meanings depending on the application and context. In the context of software architecture, data flow relates to stream processing or reactive programming. Software architecture Dataf ...

graph is a list of nodes that form an acyclic graph. Nodes have inputs and outputs. Each node is a call to an operator. Metadata documents the graph. Built-in operators are to be available on each ONNX-supporting framework.

References

External links

* * {{Microsoft FOSS Microsoft free software Software using the Apache license Neural network data exchange formats 2017 software