GANs make it possible to generate images by confronting a generator and a discriminator which will seek to differentiate the generated images from the real images.
A conditional GAN includes as an input parameter a class that lets you tell the GAN exactly what you want it to generate.
The StackGAN (SGAN) algorithm is placed in the category of CGAN because it will stack the layers of GAN to generate photorealistic images of high precision that will correspond to the textual description that will have been given.
Welcome, my name is Eric Soupet and I am the administrator of the site elodees.com. elodees.com is a state of the art of Artificial Intelligence and aims to be collaborative, you can now offer content such as articles, events, tutorials, ... so don't hesitate !
