Introducing GANs
To understand GANs, we need to understand two terms: generator and discriminator. First, we should have a reasonable sample of images (100-1000 images) of an object. A generative network (generator) learns representation from a sample of images and then generates images similar to the sample of images. A discriminator network (discriminator) is one that looks at the image generated by the generator network and the original sample of images and classifies images as original or generated (fake) ones.
The generator network tries to generate images in such a way that the discriminator classifies the images as real. The discriminator network tried to classify the generated images as fake and the images in the original sample as real.
Essentially, the adversarial term in GAN represents the opposite nature of the two networks—a generator network, which generates images to fool the discriminator network, and a discriminator network that classifies each image...
