Deploying Machine Learning models with TensorFlow Serving -- an introduction

This post covers all steps required to start serving Machine Learning models as web services with TensorFlow Serving, a flexible and high-performance serving system¹. In this example, we will setup a virtual environment in which we will generate synthetic data for a regression problem, train multiple models and finally deploy them as web services, accessing predictions from REST APIs. The only prerequisite for this tutorial is a working machine with Python² and Docker Engine³ installed. We will finally use curl⁴ to write API calls and consume the Machine Learning models through their prediction endpoints. A virtual environment is a self-consistent Python environment that can be created to manage and segregate projects: it provides isolation so that the dependencies do not affect other packages on the same operating system.