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


In the first part of this chapter, you and Pluto learn about the image augmentation concepts for classification. Pluto grouped the filters into geometric transformations, photometric transformations, and random erasing to make the image filters more manageable.

When it came to geometric transformations, Pluto covered horizontal and vertical flipping, cropping and padding, rotating, warping, and translation. These filters are suitable for most image datasets, and there are other geometric transformations, such as tilting or skewing. Still, Pluto followed the golden image augmentation rule for selecting a filter that improves prediction accuracy described in a published scholarly paper.

This golden rule is more suitable for photometric transformations because there are about 70 image filters in the Albumentations library and hundreds more available in other image augmentation libraries. This chapter covered the most commonly used photometric transformations cited in published...