The primary goal of the discriminator network is to identify whether the provided image is fake or real. It does this by passing the image through a series of downsampling layers and some classification layers. In other words, it predicts whether the image is real or fake. Like the other networks, the discriminator network is another deep convolutional network. It contains several convolutional blocks. Each convolutional block contains a convolutional layer, a batch normalization layer, and an activation function, apart from the first convolutional block, which doesn't have the batch normalization layer. The configuration of the discriminator network will be covered in the Keras implementation of Age-cGAN section.