Deep Learning: Introduction to GANs

Generative Adversarial Networks with Python and Tensorflow

In this course you will learn from scratch how to implement GANs to any of your projects. We will start with by breaking down a GAN into its parts and analyzing them. Then we will look at the loss functions we will be using and the Frechet Inception Distance. Finally we will take all this new information and apply it using Python and Tensorflow to the MNIST dataset. The code will be written such that you can use it for any of your image-based projects.

What you’ll learn

  • Understand the principles of GANs and how they work internally.
  • The mathematics behind four loss functions: Minimax, Non-Saturating, Least Squares, and Wasserstein.
  • How to determine the quality of the data a GAN produces.
  • How to generate numbers from the MNIST Dataset.
  • Apply GAN to new datasets.

Course Content

  • Theoretical Background –> 8 lectures • 48min.
  • Coding the GAN in Tensorflow –> 7 lectures • 1hr 12min.

Deep Learning: Introduction to GANs

Requirements

  • It is recommended that you know Python and the basics of Tensorflow.
  • You need to have an intermediate understanding on Neural Networks and the math behind them.

In this course you will learn from scratch how to implement GANs to any of your projects. We will start with by breaking down a GAN into its parts and analyzing them. Then we will look at the loss functions we will be using and the Frechet Inception Distance. Finally we will take all this new information and apply it using Python and Tensorflow to the MNIST dataset. The code will be written such that you can use it for any of your image-based projects.