Training Generative Adversarial Networks (GANs) in PyTorch

- by Vivek Patel

Before we start...

What is Generative adversarial networks (GANs)?

Generative adversarial networks (GANs) are an exciting recent innovation in machine learning. GANs are generative models: they create new data instances that resemble your training data. For example, GANs can create images that look like photographs of human faces, even though the faces don't belong to any real person.

These images were created by a GAN:

more info at https://thispersondoesnotexist.com/

This notebook is a minimum demo for GAN. Since PaperSpace allows maximum run time limit of 6 hrs in free tier, we will only train a lightweight model in this notebook.

Background: What is a Generative Model?

What does "generative" mean in the name "Generative Adversarial Network"? "Generative" describes a class of statistical models that contrasts with discriminative models.
Informally:

• Generative models can generate new data instances.
• Discriminative models discriminate between different kinds of data instances.

in other words There are two neural networks: a Generator and a Discriminator.

• The generator generates a latent vector(random vector/random tensor/random matrix)
• the discriminator attempts to detect whether a given sample is "real" (picked from the training data) or "fake" (generated by the generator).

Training happens in tandem: we train the discriminator for a few epochs, then train the generator for a few epochs, and repeat. This way both the generator and the discriminator get better at doing their jobs.

1. About dataset

Orignal dataset :-Wiki-Art : Visual Art Encyclopedia

Subset dataset :- art-portraits

Orignal dataset size :- 38GB

Subset dataset size :- 1.46GB

. /root ├── Training GAN on gpu.ipynb ├── art-portraits │ └── Portraits └── image-1 └── image-2 └── image-n

modeling objective Generative modeling is an unsupervised learning task in machine learning that involves automatically discovering and learning the regularities or patterns in input data in such a way that the model can be used to generate or output new examples that plausibly could have been drawn from the original dataset.

Let's install required libraries