Code implementation – generator

Now, it's time for the interesting part! As well as interesting, the following preparation steps will make your adventure in GAN coding much easier to follow. The Generator code has two core changes, which we covered in the earlier pseudocode step. In this section, we'll go over the implementation of the code's two core changes, along with the deep convolutional generator.

Getting ready

Perform a directory check, as follows:

DCGAN
├── data
├── docker
├── README.md
├── run.sh
├── scripts
└── src
    ├── generator.py
    ├── save_to_npy.py

In this section, we will build the generator.py script. You can either build it from scratch or take Generator.py from Chapter 3, My First GAN in Under 100 Lines, and upgrade it to accommodate DCGAN capabilities.

The following script may seem like a long block of text, but fear not!

How to do it...

As you should know, there is a set of key imports for each of the classes we use—make sure that you have them at the top of your file...