GAN & cGAN tutorial.
Filipe PENNA CERAVOLO SOARES
Part1: DC-GAN
- In this part, generative adversarial network (GAN) has been trained to generate new handwritten digits, after feeding it with pictures from the MNIST database
- To do so, the DCGAN tutorial of pytorch has been followed. This tutorial generate new celebrities after showing it pictures of many real celebrities.
- To adapt this tutorial to the MNIST database, the most relevant change in its implematation reflects the change of number of channels in the training images (from 3 [RGB] to 1 [Black and White]).