How to deploy Machine Learning models with TensorFlow. Part 2-- containerize it!

As described in the Part 1, I wanted to deploy my Deep Learning model into production. I've shown how to prepare the model for TensorFlow Serving. We exported the GAN model as Protobuf and it is now ready to be hosted. TensorFlow Serving implements a server that processes incoming requests and forwards them to a model. This server could be running somewhere, most probably, at your Cloud provider (such as Amazon AWS, Google Cloud Platform, Microsoft Azure), to be available to the world.