MachineLearningNotebooks/onnx

ONNX on Azure Machine Learning

These tutorials show how to create and deploy ONNX models in Azure Machine Learning environments using ONNX Runtime for inference. Once deployed as a web service, you can ping the model with your own set of images to be analyzed!

Tutorials

• Obtain ONNX model from ONNX Model Zoo and deploy with ONNX Runtime inference - Handwritten Digit Classification (MNIST)
• Obtain ONNX model from ONNX Model Zoo and deploy with ONNX Runtime inference - Facial Expression Recognition (Emotion FER+)
• Obtain ONNX model from ONNX Model Zoo and deploy with ONNX Runtime inference - Image Recognition (ResNet50)
• Convert ONNX model from CoreML and deploy - TinyYOLO
• Train ONNX model in PyTorch and deploy - MNIST

Documentation

• ONNX Runtime Python API Documentation
• Azure Machine Learning API Documentation

Related Articles

• Building and Deploying ONNX Runtime Models
• Azure AI – Making AI Real for Business
• What’s new in Azure Machine Learning

License

Copyright (c) Microsoft Corporation. All rights reserved.
Licensed under the MIT License.

Acknowledgements

These tutorials were developed by Vinitra Swamy and Prasanth Pulavarthi of the Microsoft AI Frameworks team and adapted for presentation at Microsoft Ignite 2018.