Generative Adversarial Networks Projects

Building and compiling the networks

In this section, let's build the essential networks and prepare them for training. Perform the steps as follows:

1. Start by defining the optimizer required for the training, as shown in the following code:

# Define the common optimizercommon_optimizer = Adam(0.0002, 0.5)

We will use the Adam optimizer with the learning_rate equal to 0.0002, and the beta_1 value equal to 0.5.

2. Start by creating the discriminator networks, as shown in the following code:

discriminatorA = build_discriminator()discriminatorB = build_discriminator()

As mentioned in the The Architecture of the discriminator network section, a CycleGAN has two discriminator networks.

3. Next, compile the networks, as follows:

discriminatorA.compile( ...