ONNX

Open neural network exchange format. Interoperable AI models across frameworks and hardware.

About ONNX

ONNX (Open Neural Network Exchange) is an open format built to represent machine learning models. It defines a common set of operators and a file format to enable AI developers to use models with various frameworks, tools, and runtimes.

Key Features

Framework-agnostic model format
ONNX Runtime for fast inference
Support for PyTorch, TF, Sklearn
Hardware acceleration (GPU, NPU)
Model optimization tools
Edge & mobile deployment

Why choose ONNX?

ONNX is an open source alternative to TensorFlow SavedModel, TorchScript. Licensed under Apache-2.0, it gives you full access to the source code and the freedom to modify, self-host, and contribute. It is available as a desktop or web application.