The primary goal of the generator is to generate an image of a dimension of (64, 64, 3). It takes a 100-dimensional latent vector and some extra information, y, and tries to generate realistic images. The generator network is a deep convolutional neural network too. It is made up of dense, upsampling, and convolutional layers. It takes two input values: a noise vector and a conditioning value. The conditioning value is the additional information provided to the network. For the Age-cGAN, this will be the age. The configuration of the generator network will be covered in the Keras implementation of Age-cGAN section.