Experimental Setup: Generating Sequences with GANs

Understand the data preprocessing, implementation of auxiliary functions, and loss functions.

We'll cover the following

Data
Auxiliary training functions

In this lesson, we will start by implementing methods that are necessary for preparing and loading our data during training. Next, we will learn to implement auxiliary functions that are required for the WGAN-GP. Lastly, we are going to write code to set up training and the training loop itself.

Data

We will focus on the One Billion Word Benchmark dataset that was proposed in 2013 in the paper “One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling” by Ciprian Chelba et al. This dataset can be downloaded from here.

We will start with the imports that include the libraries and functions:

Get hands-on with 1400+ tech skills courses.

Getting Started

Deep Learning Basics and Environment Test

Introduction to Generative Models

Implementing Our First GAN

Evaluating Our First GAN

Improving Our First GAN

Synthesizing and Manipulating Images with GANs

Progressive Growing of GANs

Generation of Discrete Sequences Using GANs

Text-to-Image Synthesis with GANs

Speech Enhancement with GANs

TequilaGAN—Identifying GAN Samples

What’s Next in GANs

Conclusion

Appendix

Experimental Setup: Generating Sequences with GANs

Data