Files
MachineLearningNotebooks/how-to-use-azureml/deployment/onnx
Roope Astala b00f75edd8 version 1.0.10
2019-01-28 15:30:17 -05:00
..
2019-01-14 15:13:30 -05:00

ONNX on Azure Machine Learning

These tutorials show how to create and deploy Open Neural Network eXchange (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

  1. Configure your Azure Machine Learning Workspace

Obtain models from the ONNX Model Zoo and deploy with ONNX Runtime Inference

  1. Handwritten Digit Classification (MNIST)
  2. Facial Expression Recognition (Emotion FER+)

Demo Notebooks from Microsoft Ignite 2018

Note that the following notebooks do not have evaluation sections for the models since they were deployed as part of a live demo. You can find the respective pre-processing and post-processing code linked from the ONNX Model Zoo Github pages (ResNet, TinyYoloV2), or experiment with the ONNX models by running them in the browser.

  1. Image Recognition (ResNet50)
  2. Convert Core ML Model to ONNX and deploy - Real Time Object Detection (TinyYOLO)

Documentation

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.