Hands-On Machine Learning for Algorithmic Trading

Combining both networks to define the GAN

The combined model consists of the stacked generator and discriminator and trains the former to fool the latter:

# The generator takes noise as input and generates imgsz = Input(shape=(latent_dim,))img = generator(z)# For the combined model we will only train the generatordiscriminator.trainable = False# The discriminator takes generated images as input and determines validityvalid = discriminator(img)# The combined model (stacked generator and discriminator)# Trains the generator to fool the discriminatorcombined = Model(z, valid)combined.compile(loss='binary_crossentropy', optimizer=optimizer)