onnx/onnx
Open standard for machine learning interoperability
What it solves
ONNX (Open Neural Network Exchange) solves the problem of interoperability between different AI frameworks. It allows developers to move models between different tools, frameworks, and hardware, streamlining the path from research to production by providing a common format for both deep learning and traditional machine learning models.
How it works
ONNX defines an open source format and an extensible computation graph model. This includes standard data types and definitions for built-in operators, which allows models to be represented in a consistent way regardless of the original framework used to create them. The project currently focuses primarily on the capabilities needed for inferencing (scoring).
Who it’s for
AI developers who need to move their models across different frameworks or deploy them to various hardware targets without being locked into a single ecosystem.
Highlights
- Open Ecosystem: An open source format supported by a wide range of frameworks and tools.
- Extensible Graph Model: Uses a computation graph to represent AI models.
- Interoperability: Enables seamless movement of models between different AI tools.
- Programming Utilities: Includes tools for shape and type inference, graph optimization, and opset version conversion.