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


Image segmentation consists of the original image and an accompanying mask image. The goal is to determine whether a pixel belongs to a list of objects. For example, an urban photograph consists of streets, street signs, cars, trucks, bicycles, buildings, trees, and pedestrians. Image segmentation’s job is to decide whether this pixel belongs to a car, tree, or other objects.

Image segmentation and image classification share the same transformations. In other words, most geometric transformations, such as flipping, rotating, resizing, cropping, and transposing, work with the original image and mask image in image segmentation. Photometric transformations, such as brightness, contrast, and FancyPCA, can technically be done with Python, but the filter does not alter the mask image. On the other hand, filters such as noise injection and random erasing are unsuitable for segmentation because they add or replace pixels in the original image.

Throughout this chapter...