Our objective is to create a model capable of generating realistic human images that do not exist in reality. (In future, I will upload a number of use cases on GAN and its variants).

The technology behind these kinds of AI is called a GAN, or “Generative Adversarial Network”. A GAN takes a different approach to learning than other types of neural networks(NN). GANs algorithmic architectures that use two neural networks called a Generator and a Discriminator, which “compete” against one another to create the desired result. The Generator’s job is to create realistic looking fake images, while the Discriminator’s job is to distinguish between real images and fake images. If both are functioning at high levels, the result is images that are seemingly identical real-life photos.

GAN Architecture:

Dataset can be downloaded from: https://www.kaggle.com/jessicali9530/celeba-dataset

You can follow this article on www.theaidream.com to understand it step by step approch and also check my kaggle notebook for implementation.