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

1. Start by specifying the values for different hyperparameters:

dis_input_shape = (64, 64, 64, 1)
dis_filters = [64, 128, 256, 512, 1]
dis_kernel_sizes = [4, 4, 4, 4, 4]
dis_strides = [2, 2, 2, 2, 1]
dis_paddings = ['same', 'same', 'same', 'same', 'valid']
dis_alphas = [0.2, 0.2, 0.2, 0.2, 0.2]
dis_activations = ['leaky_relu', 'leaky_relu', 'leaky_relu', 'leaky_relu', 'sigmoid']
dis_convolutional_blocks = 5

2. Next, create an input layer to allow the network to take input. The input to the discriminator network is a 3D image that has a shape of 64x64x64x1:

dis_input_layer = Input(shape=dis_input_shape)

3. Then, add the first 3D convolution block, shown as follows:

# The first 3D Convolution block
a = Conv3D(filters=dis_filters[0],
           kernel_size=dis_kernel_sizes[0],
           strides=dis_strides[0],
           padding=dis_paddings[0])(dis_input_layer)
a = BatchNormalization()(a, training=True)
a = LeakyReLU(alphas[0])(a)

4. After that, add four more 3D convolution blocks, shown as follows:

# The next 4 3D Convolutional Blocks
for i in range(dis_convolutional_blocks - 1):
    a = Conv3D(filters=dis_filters[i + 1],
               kernel_size=dis_kernel_sizes[i + 1],
               strides=dis_strides[i + 1],
               padding=dis_paddings[i + 1])(a)
    a = BatchNormalization()(a, training=True)
    if dis_activations[i + 1] == 'leaky_relu':
        a = LeakyReLU(dis_alphas[i + 1])(a)
    elif dis_activations[i + 1] == 'sigmoid':
        a = Activation(activation='sigmoid')(a)

5. Next, create a Keras model and specify the inputs and the outputs for the discriminator network:

dis_model = Model(inputs=dis_input_layer, outputs=a)

6. Wrap the complete code for the discriminator network inside a function, given as follows:

def build_discriminator():
    """
    Create a Discriminator Model using hyperparameters values defined as follows
    :return: Discriminator network
    """

    dis_input_shape = (64, 64, 64, 1)
    dis_filters = [64, 128, 256, 512, 1]
    dis_kernel_sizes = [4, 4, 4, 4, 4]
    dis_strides = [2, 2, 2, 2, 1]
    dis_paddings = ['same', 'same', 'same', 'same', 'valid']
    dis_alphas = [0.2, 0.2, 0.2, 0.2, 0.2]
    dis_activations = ['leaky_relu', 'leaky_relu', 'leaky_relu', 
                       'leaky_relu', 'sigmoid']
    dis_convolutional_blocks = 5

    dis_input_layer = Input(shape=dis_input_shape)

    # The first 3D Convolutional block
    a = Conv3D(filters=dis_filters[0],
               kernel_size=dis_kernel_sizes[0],
               strides=dis_strides[0],
               padding=dis_paddings[0])(dis_input_layer)
    a = BatchNormalization()(a, training=True)
    a = LeakyReLU(dis_alphas[0])(a)

    # Next 4 3D Convolutional Blocks
    for i in range(dis_convolutional_blocks - 1):
        a = Conv3D(filters=dis_filters[i + 1],
                   kernel_size=dis_kernel_sizes[i + 1],
                   strides=dis_strides[i + 1],
                   padding=dis_paddings[i + 1])(a)
        a = BatchNormalization()(a, training=True)
        if dis_activations[i + 1] == 'leaky_relu':
            a = LeakyReLU(dis_alphas[i + 1])(a)
        elif dis_activations[i + 1] == 'sigmoid':
            a = Activation(activation='sigmoid')(a)

    dis_model = Model(inputs=dis_input_layer, outputs=a)
    print(dis_model.summary())
 return dis_model

In this section, we created a Keras model for the discriminator network. We are now ready to train a 3D-GAN.