Keras Deep Learning Cookbook

Building a discriminator

A discriminator can also be made into a sequential model by going in the opposite direction:

• The first layer is to flatten the input_shape of 28,28,1
• Add a dense layer with an output (*, 512)
• Add an activation function of Leaky ReLU
• Add another dense layer, which outputs (*, 256)
• Add another activation function of leaky ReLU

• Add a final output of (*, 1):

def build_discriminator(self):  model = Sequential()  model.add(Flatten(input_shape=self.img_shape))  model.add(Dense(512))  model.add(LeakyReLU(alpha=0.2))  model.add(Dense(256))  model.add(LeakyReLU(alpha=0.2))  model.add(Dense(1, activation='sigmoid'))  model.summary()  img = Input(shape=self.img_shape)  validity = model(img)  return Model(img, validity)