To implement the generator network, we need to create a Keras model and add the neural network layers. The steps required to implement the generator network are as follows:

1. Start by specifying the values for different hyperparameters:

z_size = 200
gen_filters = [512, 256, 128, 64, 1]
gen_kernel_sizes = [4, 4, 4, 4, 4]
gen_strides = [1, 2, 2, 2, 2]
gen_input_shape = (1, 1, 1, z_size)
gen_activations = ['relu', 'relu', 'relu', 'relu', 'sigmoid']
gen_convolutional_blocks = 5

2. Next, create an input layer to allow the network to take input. The input to the generator network is a vector sampled from a probabilistic latent space:

input_layer = Input(shape=gen_input_shape)

3. Then, add the first 3D transpose convolution (or 3D deconvolution) block, as shown in the following code:

# First 3D transpose convolution( or 3D deconvolution) block
a = Deconv3D(filters=gen_filters[0],  
             kernel_size=gen_kernel_sizes[0],
             strides=gen_strides[0])(input_layer)
a = BatchNormalization()(a, training=True)
a = Activation(activation=gen_activations[0])(a)

4. Next, add four more 3D transpose convolutions (or 3D deconvolution) blocks, shown as follows:

# Next 4 3D transpose convolution( or 3D deconvolution) blocks
for i in range(gen_convolutional_blocks - 1):
    a = Deconv3D(filters=gen_filters[i + 1], 
                 kernel_size=gen_kernel_sizes[i + 1],
                 strides=gen_strides[i + 1], padding='same')(a)
    a = BatchNormalization()(a, training=True)
    a = Activation(activation=gen_activations[i + 1])(a)

5.  Then, create a Keras model and specify the inputs and the outputs for the generator network:

model = Model(inputs=input_layer, outputs=a)

6. Wrap the entire code for the generator network inside a function called build_generator():

def build_generator():
 """
 Create a Generator Model with hyperparameters values defined as follows
 :return: Generator network
 """
 z_size = 200
 gen_filters = [512, 256, 128, 64, 1]
 gen_kernel_sizes = [4, 4, 4, 4, 4]
 gen_strides = [1, 2, 2, 2, 2]
 gen_input_shape = (1, 1, 1, z_size)
 gen_activations = ['relu', 'relu', 'relu', 'relu', 'sigmoid']
 gen_convolutional_blocks = 5

 input_layer = Input(shape=gen_input_shape)

 # First 3D transpose convolution(or 3D deconvolution) block
 a = Deconv3D(filters=gen_filters[0], 
 kernel_size=gen_kernel_sizes[0],
 strides=gen_strides[0])(input_layer)
 a = BatchNormalization()(a, training=True)
 a = Activation(activation='relu')(a)

 # Next 4 3D transpose convolution(or 3D deconvolution) blocks
 for i in range(gen_convolutional_blocks - 1):
 a = Deconv3D(filters=gen_filters[i + 1], 
 kernel_size=gen_kernel_sizes[i + 1],
 strides=gen_strides[i + 1], padding='same')(a)
 a = BatchNormalization()(a, training=True)
 a = Activation(activation=gen_activations[i + 1])(a)

 gen_model = Model(inputs=input_layer, outputs=a)

 gen_model.summary()
 return gen_model

We have successfully created a Keras model for the generator network. Next, create a Keras model for the discriminator network.