Generative Adversarial Networks Projects

Stage-I

A Stage-I StackGAN contains both a generator network and a discriminator network. It also has a text encoder network and a Conditional Augmentation network (CA network), which are explained in detail in the following section. The generator network gets the text conditioning variable (), along with a noise vector (x). After a set of upsampling layers, it produces a low-resolution image with dimensions of 64x64x3. The discriminator network takes this low-resolution image and tries to identify whether the image is real or fake. The generator network is a network with a set of downsampling layers, followed by a concatenation and then a ...