Now, it's time to implement the second part of the network that will be trying to replicate the original input images using the latent space z. We'll be using tf.variable_scope for this function as well.

So, let's define the function which will return a generated image by the generator:

def generator(z_latent_space, output_channel_dim, is_train=True):

    
    with tf.variable_scope('generator', reuse=not is_train):
        
        #leaky relu parameter
        leaky_param_alpha = 0.2
    
        fully_connected_layer = tf.layers.dense(z_latent_space, 2*2*512)
        
        #reshaping the output back to 4D tensor to match the accepted format for convolution layer
        reshaped_output = tf.reshape(fully_connected_layer, (-1, 2, 2, 512))
        normalized_output = tf.layers.batch_normalization(reshaped_output, training=is_train)
        leaky_relu_output = tf.maximum(leaky_param_alpha * normalized_output, normalized_output)
    
        conv_layer_1 = tf.layers.conv2d_transpose(leaky_relu_output, 256, 5, 2, 'valid')
        normalized_output = tf.layers.batch_normalization(conv_layer_1, training=is_train)
        leaky_relu_output = tf.maximum(leaky_param_alpha * normalized_output, normalized_output)
    
        conv_layer_2 = tf.layers.conv2d_transpose(leaky_relu_output, 128, 5, 2, 'same')
        normalized_output = tf.layers.batch_normalization(conv_layer_2, training=is_train)
        leaky_relu_output = tf.maximum(leaky_param_alpha * normalized_output, normalized_output)
    
        logits_layer = tf.layers.conv2d_transpose(leaky_relu_output, output_channel_dim, 5, 2, 'same')
        output = tf.tanh(logits_layer)
    
        return output