Code implementation – discriminator

The discriminator's purpose is to determine whether the generated sample is real or fake—there's a balance to strike in order to make sure the discriminator is just good enough to keep the generator moving in the right direction. The discriminator class we'll use is 3D convolutions to determine whether 3D samples are real or fake.

Getting ready

The generator is now complete and we're moving on to develop the discriminator class. In the src folder, add the discriminator.py file.

 

 

You should have the following directory structure:

├── data
├── docker
│   ├── build.sh
│   ├── clean.sh
│   ├── Dockerfile
│   └── kaggle.json
├── out
├── README.md
├── run_autoencoder.sh
└── src
    ├── discriminator.py
    ├── encoder_model.h5
    ├── encoder.py
    ├── generator.py
    ├── x_test_encoded.npy
    └── x_train_encoded.npy

How to do it...

The Discriminator class needs an initialization step, a block method, a model method, and a summary method. The following recipe...