The DCGAN architecture simply requires updates for the model of the discriminator and generator. We will also need to update our training step to improve convergence. The MNIST data we used in the first example is the simplest of the examples we can work with. Convergence for GANs, as you will remember, is one of the hardest parts about building such an architecture, but the DCGAN architecture helps ensure that convergence happens reliably. We'll take a detailed look at convergence with the help of pseudocode in the next section.