Book Image

Data Augmentation with Python

By : Duc Haba
Book Image

Data Augmentation with Python

By: Duc Haba

Overview of this book

Data is paramount in AI projects, especially for deep learning and generative AI, as forecasting accuracy relies on input datasets being robust. Acquiring additional data through traditional methods can be challenging, expensive, and impractical, and data augmentation offers an economical option to extend the dataset. The book teaches you over 20 geometric, photometric, and random erasing augmentation methods using seven real-world datasets for image classification and segmentation. You’ll also review eight image augmentation open source libraries, write object-oriented programming (OOP) wrapper functions in Python Notebooks, view color image augmentation effects, analyze safe levels and biases, as well as explore fun facts and take on fun challenges. As you advance, you’ll discover over 20 character and word techniques for text augmentation using two real-world datasets and excerpts from four classic books. The chapter on advanced text augmentation uses machine learning to extend the text dataset, such as Transformer, Word2vec, BERT, GPT-2, and others. While chapters on audio and tabular data have real-world data, open source libraries, amazing custom plots, and Python Notebook, along with fun facts and challenges. By the end of this book, you will be proficient in image, text, audio, and tabular data augmentation techniques.
Table of Contents (17 chapters)
Part 1: Data Augmentation
Part 2: Image Augmentation
Part 3: Text Augmentation
Part 4: Audio Data Augmentation
Part 5: Tabular Data Augmentation


This chapter was not a typical one in this book because we discussed more theory than practical data augmentation techniques. At first, the link between data biases and data augmentation seems tenuous. Still, as you begin to learn about computational, human, and systemic biases, you see the strong connection because they all share the same goal of ensuring successful ethical AI system usage and acceptance.

In other words, data augmentation increases the AI’s prediction accuracy while reducing the data biases in augmenting, ensuring the AI forecast has fewer false-negative and true-negative outcomes.

The computational, human, and systemic biases are similar but are not mutually exclusive. However, providing plenty of examples of real-world biases and observing three real-world image datasets and two real-world text datasets made these biases easier to understand.

The nature of data bias in augmenting makes it challenging to compute biases programmatically. However...