Repository files navigation

Open Neural Network Exchange (ONNX) is an open standard format for representing machine learning models. ONNX is supported bya community of partners who have implemented it in many frameworks and tools.

• Pre-trained models (validated): Many pre-trained ONNX models are provided for common scenarios in theONNX Model Zoo
• Pre-trained models (non-validated): Many pre-trained ONNX models are provided for common scenarios in theONNX Model Zoo.
• Services: Customized ONNX models are generated for your data by cloud based services (see below)
• Convert models from various frameworks (see below)

Below is a list of services that can output ONNX models customized for your data.

• Azure Custom Vision service
• Azure Machine Learning automated ML
• Lobe desktop app

Once you have an ONNX model, it can be scored with a variety of tools.

Tutorials demonstrating how to use ONNX in practice for varied scenarios across frameworks, platforms, and device types

• AI-Serving
• AWS Lambda
• Cortex
• MXNet
  • MXNet Model Server
  • AWS SageMaker and MXNet
  • MXNet to ONNX to ML.NET with SageMaker, ECS and ECR - external link
• ONNX Runtime
  • ONNX Runtime Tutorials
  • Azure ML and ONNX Runtime

• Converting SuperResolution model from PyTorch to Caffe2 with ONNX and deploying on mobile device
• Transferring SqueezeNet from PyTorch to Caffe2 with ONNX and to Android app
• Converting Style Transfer model from PyTorch to CoreML with ONNX and deploying to an iPhone
• Deploy ONNX Runtime on Mobile/Edge devices

• HuggingFace Bert Quantization with ONNX Runtime

• Convert a PyTorch model to Tensorflow using ONNX

• How to export Pytorch model with custom op to ONNX and run it in ONNX Runtime

• Netdrawer: Visualizing ONNX models
• Netron: Viewer for ONNX models
• Zetane: 3D visualizer for ONNX models and internal tensors

• Verifying correctness and comparing performance
• Example of operating on ONNX protobuf
• Float16 <-> Float32 converter
• Version conversion

• Explainable AI for ONNX models

We welcome improvements to the convertor tools and contributions of new ONNX bindings. Check outcontributor guide to get started.

Use ONNX for something cool? Send the tutorial to this repo by submitting a PR.