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

Python Notebook

This chapter’s coding lessons primarily focus on downloading real-world datasets from the Kaggle website. The later chapters rely on or reuse these fetching functions.

In the previous chapter, you learned about this book’s general rules for development on the Python Notebook. The object-oriented class named Pluto contains the methods and attributes, and you add new methods to Pluto as you learn new concepts and techniques. Review Chapter 1 if you are uncertain about the development philosophy.

In this book, the term Python Notebook is used synonymously for Jupyter Notebook, JupyterLab, and Google Colab Notebook.

Fun challenge

Pluto challenges you to change the object’s name from Pluto to any other name. If you do change the name, then substitute that name where you see Pluto in your text and code. For example, if you change the object name to Sandy, then pluto.draw_batch_image() becomes sandy.draw_batch_image().

Starting with this...