In Microsoft Build 2018 , Microsoft had update the Custom Vision with ONNX with Windows Machine Learning.
What is ONNX ?
Open Neural Network Exchange Format -ONNX- enables models to be trained in one framework and transferred to another for inference. It is just a file format on top of protobuf which carries the computational graph, as well as all the parameters required for making predictions.
To know more about Windows Machine Learning :
Now we proceed to hand-on:
1. We go to https://customvision.ai/ and login with your Microsoft Account.
2. If you does not had any of the project , please create one.
3. If you got existing project, please follow me.
4. Go to Settings of your project.
5. Go to your project Domain change to XXX(Compact) and Save.
6. Click the button Train.
7. Go to Performance Tab and click Export.
8. Select TensorFlow to export ONNX model.
9. Drop your *model.onnx file into your project's Assets folder.
10. Under Solutions Explorer/ Assets Folder add model file to project by selecting Add Existing Item.
11. Change properties of model just added: "Build Action" -> "Content" and "Copy to Output Directory" -> "Copy if newer"
12. Debug your Source Code.
Here with the GitHub Repo.
Happy Coding. :)