Deep Convolutional Generative Adversarial Network using PyTorch
Learn how to generate MNIST images with a DCGAN using PyTorch
This post will learn to create a DCGAN using PyTorch on the MNIST dataset.
Prerequisites
A sample implementation using CNN
Understanding Deep Convolutional GAN
GANs were invented by Ian Goodfellow in 2014 and first described in the paper Generative Adversarial Nets.
GAN is Generative Adversarial Network is a generative model to create new data instances that resemble the training data set. GAN is implemented using two neural networks: Generator and Discriminator
Generator and Discriminator
The Generator’s objective is to learn the data distribution for the training data to produce fake images that resemble the training data.
The Discriminator is a classifier whose objective is to distinguish the real data from the fake data generated by the Generator. Every time the Discriminator detects the fake data generated by the Generator, then the Generator is penalized.
The Generator and Discriminator are pitted against each other as the Generator tries to fool the…