Generative Adversarial Networks Projects

Building and compiling the networks

In this section, we will go through the different steps required to build and compile the networks:

1. Build and compile the VGG19 network:

vgg = build_vgg()vgg.trainable = Falsevgg.compile(loss='mse', optimizer=common_optimizer, metrics=            ['accuracy'])

To compile VGG19, use mse as the loss, accuracy as the metrics, and common_optimizer as the optimizer. Before compiling the network, disable the training, as we don't want to train the VGG19 network.

2. Next, build and compile the discriminator network, as follows:

discriminator = build_discriminator()discriminator.compile(loss='mse', optimizer=common_optimizer,                       metrics=['accuracy'])

To compile the discriminator network, use mse as the loss, accuracy as the ...