TF Serving in the Docker containers

Docker is a platform for packaging and deploying the application in containers. If you do not already know about the Docker containers, then visit the tutorials and information at the following link: https://www.docker.com/what-container. 

We can also install and run the TensorFlow Serving in the Docker containers. The instructions for Ubuntu 16.04 provided in this section are derived from the links on TensorFlow's official website: 

• https://www.tensorflow.org/serving/serving_inception
• https://www.tensorflow.org/serving/serving_basic

Let us dive right in!

Installing Docker

We install Docker as follows:

1. First, remove the previous installations of Docker:

$ sudo apt-get remove docker docker-engine docker.io

2. Install the pre-requisite software:

$ sudo apt-get install \
    apt-transport-https \
    ca-certificates \
    curl \
    software-properties-common

3. Add the GPG key for Docker repositories:

$ curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key...