# Multiple TensorFlow Graphs from Cognitive Services - Custom Vision Service

https://jaredrhodes.com/blog/multiple-tensorflow-graphs-from-cognitive-services-custom-vision-service/

For one project, there was a need for multiple models within the same Python application. These models were trained using the [Cognitive Services: Custom Vision Service](https://azure.microsoft.com/en-us/services/cognitive-services/custom-vision-service/). There are two steps to using an exported model:

1. Prepare the image
2. Classify the image

## Prepare an image for prediction

https://gist.github.com/QiMata/6ebb15a8e42450e57c3fe48b44e920cb

## Classify the image

To run multiple models in Python was fairly simple. Simply call *tf.reset\_default\_graph()* after saving the loaded session into memory.

https://gist.github.com/QiMata/b63c7d0699173067d4c60c9f06a63273

After the CustomVisionCategorizer is created, just call *score* and it will score with the labels in the map.