In this chapter, we covered the offerings from Microsoft AI and the Azure cloud for performing deep learning on websites. We saw how the Face API can be used to predict the gender and age of people in images, as well as how the Text Analytics API can be used to predict the language of a given text and the key phrases in the provided text or the sentiment of any sentence. Finally, we created a deep learning model using CNTK on the MNIST dataset. We saw how the model can be saved and then deployed via a Django-based web application in the form of an API. This deployment of the saved model via Django can be easily adapted for other deep learning frameworks, such as TensorFlow or PyTorch.
In the next chapter, we will discuss a generalized framework for building production-grade deep learning applications using Python.
