Generative Adversarial Networks Projects

Training the discriminator network

The steps given in this section show how to train the discriminator network. This is a continuation of the last series of steps:

1. Generate fake high-resolution images using the generator network:

generated_high_resolution_images =           generator.predict(low_resolution_images)

2. Create a batch of real labels and fake labels:

    real_labels = np.ones((batch_size, 16, 16, 1))    fake_labels = np.zeros((batch_size, 16, 16, 1))

3. Train the discriminator network on real images and real labels:

d_loss_real = discriminator.train_on_batch(high_resolution_images,    real_labels)

4. Train the discriminator on generated images and fake labels:

d_loss_fake = discriminator.train_on_batch(generated_high_resolution_images, fake_labels) ...