Deploy Your First Deep Learning Model On Kubernetes With Python, Keras, Flask, and Docker

This post demonstrates a *basic* example of how to build a deep learning model with Keras, serve it as REST API with Flask, and deploy it using Docker and Kubernetes. This is NOT a robust, production example. This is a quick guide for anyone out there who has heard about Kubernetes but hasn't tried it out yet. To that end, I use Google Cloud for every step of this process. The reason is simple -- I didn't feel like installing Docker and Kubernetes on my Windows 10 Home laptop. The additional benefit to you all following along is reproducing my steps should be much easier as you can run everything using the exact specifications I used.