ONNX
An open standard format for representing machine learning models to enable interoperability between frameworks.
What is ONNX?
ONNX (Open Neural Network Exchange) is an open standard format for representing machine learning models that enables interoperability between different AI frameworks. It defines an extensible computation graph model with built-in operators and standard data types, allowing models to be trained in one framework and deployed in another. The project focuses on capabilities needed for model inferencing (scoring) and aims to streamline the path from research to production.
AI and machine learning developers, researchers, and engineers who work across multiple frameworks or need to deploy models in different environments. It's particularly valuable for teams building production ML systems that require framework flexibility.
ONNX provides a vendor-neutral, open standard that breaks down framework lock-in and enables true interoperability in the machine learning ecosystem. Its wide industry adoption and extensible design make it the de facto standard for model exchange between different AI tools and hardware platforms.
Overview
Open standard for machine learning interoperability
Use Cases
Best For
- Converting models between different machine learning frameworks
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
