Open Neural Network Exchange
 | |
| Developer(s) | Facebook, Microsoft |
|---|---|
| Initial release | September 2017 |
| Stable release | 1.17.0[1]
/ 1 October 2024 |
| Repository | |
| Written in | C++, Python |
| Operating system | Windows, Linux |
| Type | Artificial intelligence ecosystem |
| License | MIT License |
| Website | onnx |
The Open Neural Network Exchange (ONNX) is an open-source artificial intelligence ecosystem.[2] ONNX is available on GitHub.
History
In September 2017 Facebook and Microsoft introduced a system for switching between machine learning frameworks such as PyTorch and Caffe2.[3] Later, IBM, Huawei, Intel, AMD, ARM and Qualcomm announced support for the initiative.[2]
In October 2017, Microsoft announced that it would add its Cognitive Toolkit and Project Brainwave platform to the initiative.[2]
In November 2019 ONNX was accepted as graduate project in Linux Foundation AI.
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.[4]
Shared optimization
Allow hardware vendors and others to improve the performance of artificial neural networks of multiple frameworks at once by targeting the ONNX representation.[4]
Contents
ONNX provides definitions of an extensible computation graph model, built-in operators and standard data types, focused on inferencing (evaluation).[4]
Each computation dataflow 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.[4]
Other partnerships
Microsoft and Facebook are part of the Partnership on AI along with Apple, Amazon, Google and IBM that works to increase public awareness and boost research.[2]
See also
- Neural Network Exchange Format
- Comparison of deep learning software
- Predictive Model Markup Language an XML-based predictive model interchange format
- PicklingTools: an open-source collection of tools for allowing C++ and Python systems to share information quickly and easily.
References
- ^ "Release 1.17.0". 1 October 2024. Retrieved 22 October 2024.
- ^ a b c d "Microsoft and Facebook's open AI ecosystem gains more support". Engadget. Retrieved 2017-10-11.
- ^ Boyd, Eric. "Microsoft and Facebook create open ecosystem for AI model interoperability". Azure Blog and Updates. Microsoft. Retrieved 15 March 2021.
- ^ a b c d "Microsoft and Facebook create open ecosystem for AI model interoperability - Microsoft Cognitive Toolkit". Microsoft Cognitive Toolkit. 2017-09-07. Retrieved 2017-10-11.
External links
- Boyd, Eric (2017-09-07). "Microsoft and Facebook create open ecosystem for AI model interoperability - Microsoft Cognitive Toolkit". Microsoft Cognitive Toolkit. Retrieved 2017-10-11.
- onnx: Open Neural Network Exchange, Open Neural Network Exchange, 2017-10-11, retrieved 2017-10-11
