Model definition for shallow DCGAN

dcgan_model.py

''' SHALLOW MODEL '''
img_shape = (32, 32, 3)
z_dim = 100
init = initializers.RandomNormal(mean=0.0, stddev=0.02)
opt = Adam(lr=0.0002, beta_1=0.5)

def build_discriminator(in_shape=img_shape):
    model = Sequential()
    
    model.add(Conv2D(64, (5,5), input_shape=in_shape, kernel_initializer=init))
    model.add(BatchNormalization())
    model.add(LeakyReLU(alpha=0.2))
    
    model.add(Conv2D(128, (5,5), strides=2, padding='same', kernel_initializer=init))
    model.add(BatchNormalization())
    model.add(LeakyReLU(alpha=0.2))
    
    model.add(Conv2D(256, (5,5), strides=2, padding='same', kernel_initializer=init))
    model.add(BatchNormalization())
    model.add(LeakyReLU(alpha=0.2))
    
    model.add(Conv2D(512, (5,5), strides=2, padding='same', kernel_initializer=init))
    model.add(BatchNormalization())
    model.add(LeakyReLU(alpha=0.2))
    
    model.add(Flatten())
    model.add(Dropout(0.4))
    model.add(Dense(1, activation='sigmoid'))
   
    model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])
    
    return model

def build_generator(latent_dim):
    model = Sequential()
    
    model.add(Dense(512*4*4, input_dim=latent_dim, kernel_initializer=init))
    model.add(LeakyReLU(alpha=0.2))
    model.add(Reshape((4, 4, 512)))
    
    model.add(Conv2DTranspose(256, (5,5), strides=2, padding='same', kernel_initializer=init))
    model.add(BatchNormalization())
    model.add(LeakyReLU(alpha=0.2))
    
    model.add(Conv2DTranspose(128, (5,5), strides=2, padding='same', kernel_initializer=init))
    model.add(BatchNormalization())
    model.add(LeakyReLU(alpha=0.2))
    
    model.add(Conv2DTranspose(64, (5,5), strides=2, padding='same', kernel_initializer=init))
    model.add(BatchNormalization())
    model.add(LeakyReLU(alpha=0.2))
    
    model.add(Conv2D(3, (3,3), activation='tanh', padding='same', kernel_initializer=init))
    
    return model

def build_gan(generator, discriminator):
    discriminator.trainable = False
    
    model = Sequential()
    model.add(generator)
    model.add(discriminator)
   
    model.compile(loss='binary_crossentropy', optimizer=opt)
    
    return model