GAN tutorial in Pytorch

What is GAN?

GAN is composed of two networks. Generator is a network that generates new data instance and Discriminator is a network that determine if the data instance is a real or fake. Generator aims to generate data instance that is hard to discriminate and Discriminator aims to have good performance at discriminating real and fake data.

I wanted to study more details about GAN with a real code.

I found a GAN code and run it using new language, Pytorch. I used to use Tensorflow but I wanted to study Pytorch.

Here is the my GAN tutorial.

GAN tutorial

To do list

• difference between DCGAN, styleGAN, Pix2pixHD
• read papers?

REFERENCE

http://intelligence.korea.ac.kr/members/wschoi/seminar/tutorial/mnist/pytorch/gan/GAN-%ED%8A%9C%ED%86%A0%EB%A6%AC%EC%96%BC/