Keras Deep Learning Cookbook

Training the GAN 

Let's look at how the model is trained:

1. First, load the dataset
2. Rescale the data
3. Generate valid and fake ground truths

4. For each iteration of an epoch, do the following:
   • Select a random batch of images
   • Generate images
   • Calculate the loss for real and fake images
   • Sample and plot the images:

def train(self, epochs, batch_size=128, sample_interval=50):    # Load the dataset    (X_train, _), (_, _) = fashion_mnist.load_data()    # Rescale -1 to 1    X_train = X_train / 127.5 - 1.    X_train = np.expand_dims(X_train, axis=3)    # Adversarial ground truths    valid = np.ones((batch_size, 1))    fake = np.zeros((batch_size, 1))    for epoch in range(epochs):        # ---------------------        #  Train Discriminator        # --------------------- # Select a random batch ...