On July 27, 2020 the article Generative Adversarial Networks: Build Your First Models was published on Real Python. In the following, you’ll find the summary and the link to the code on Github.
Generative adversarial networks (GANs) are neural networks that generate material, such as images, music, speech, or text, that is similar to what humans produce.
GANs have been an active topic of research in recent years. Facebook’s AI research director Yann LeCun called adversarial training “the most interesting idea in the last 10 years” in the field of machine learning.
In this tutorial, published on Real Python, you’ll learn:
The code is available on Github.
- What a generative model is and how it differs from a discriminative model
- How GANs are structured and trained
- How to build your own GAN using PyTorch
- How to train your GAN for practical applications using a GPU and PyTorch