Hands-On Generative Adversarial Networks with Keras

Wrapper

We add a wrapper that combines a 2D Convolution with Batchnorm and an optional ReLU. This sequence of layers is very common in this model. In using this wrapper, the code becomes more compact and easier to read:

def ConvBatchnormRelu(x, n_filters, kernel_size, strides, padding, relu=True):    x = Conv2D(n_filters, kernel_size=kernel_size, strides=strides,               padding=padding, kernel_initializer=w_init)(x)    x = BatchNormalization(gamma_initializer=g_init)(x)    if relu:        x = Activation('relu')(x)    return x

Let's take a look at the diagram provided by the authors before we implement the Discriminator and the Generator:

Source: Generative Adversarial ...