Hands-On Generative Adversarial Networks with Keras

Helper functions

We start with the necessary imports and initializations:

from keras.layers import Conv2D, Activationfrom keras.layers import Add, Lambdafrom keras.initializers import RandomNormalweight_init = RandomNormal(mean=0., stddev=0.02)

Then we use the helper function that defines a ResNet block:

from keras.layers import Conv2D, Activationfrom keras.layers import Add, Lambdafrom keras.initializers import RandomNormalweight_init = RandomNormal(mean=0., stddev=0.02)def resnet_block(input, n_blocks, n_filters, kernel_size=(1, 3)):    output = input    for i in range(n_blocks):        output = Activation('relu')(output)        output = Conv2D(filters=n_filters, kernel_size=kernel_size,                        strides=1, padding='same',                        kernel_initializer=weight_init)(output) ...