Highlights: Hello and welcome. In the previous posts, we have seen the architecture, building, and implementation of three DCGAN models using different datasets. By now, you must have gotten a fair bit of idea about Generative Adversarial Networks in general. In this post, we will go deeper into the workings of a generator in a typical GAN model. More specifically, we will understand the Latent Space which is used as an input for the generator.…
Read more

Highlights: In the previous two chapters, we built two distinct DCGAN models, one for MNIST Handwritten Digit dataset, and the other for CIFAR-10 dataset. In this chapter, we will build yet another DCGAN model. However, this time, we will use a different dataset known as the CelebA dataset. Let’s start by learning a bit about the CelebA dataset and its features. Tutorial overview: Downloading CelebA Dataset Initializing and Defining the DCGAN Model Training the DCGAN…
Read more

Highlights: In the previous post, we built a Deep Convolutional Generative Adversarial Network (DCGAN) for the MNIST Handwritten Digit Dataset. Taking forward the encouraging results we displayed in the previous chapter, let us build our first DCGAN model using the standard small image dataset, CIFAR-10. By using a small and already well-understood dataset such as CIFAR-10, we can speed up the development and training of our model so that we are can focus more on…
Read more

Highlights: In the previous posts, we brushed the surface of our book’s hero concept of Generative Adversarial Networks (GANs). We also learned about training stable GANs using Deep Convolutional Generative Adversarial Networks (DCGANs). In this post, we will dive a little bit more into the details of the GANs. We will observe their mathematical foundations through the fundamentals of probability and optimization methods. So, let’s begin. Tutorial overview: Adversarial Learning The Adversarial Game Loss Function…
Read more