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.

Related Content you might be interested in

Current Title:

Small book image
Data Augmentation with Python
Duc Haba
Apr, 2023 | 394 pages
Small book image
Data Labeling in Machine Learning with Python
Vijaya Kumar Suda
Jan, 2024 | 398 pages
Table of Contents (17 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Download the example code files
Download the color images
Conventions used
Get in touch
Share your thoughts
Download a free PDF copy of this book
1
Part 1: Data Augmentation
Part 1: Data Augmentation
Free Chapter
2
Chapter 1: Data Augmentation Made Easy
Chapter 1: Data Augmentation Made Easy
Data augmentation role
Data input types
Python Notebook
Google Colab
Programming styles
Summary
3
Chapter 2: Biases in Data Augmentation
Chapter 2: Biases in Data Augmentation
Computational biases
Human biases
Systemic biases
Python Notebook
Image biases
Text biases
Summary
4
Part 2: Image Augmentation
Part 2: Image Augmentation
5
Chapter 3: Image Augmentation for Classification
Chapter 3: Image Augmentation for Classification
Geometric transformations
Photometric transformations
Random erasing
Combining
Reinforcing your learning through Python code
Summary
6
Chapter 4: Image Augmentation for Segmentation
Chapter 4: Image Augmentation for Segmentation
Geometric and photometric transformations
Real-world segmentation datasets
Reinforcing your learning
Summary
7
Part 3: Text Augmentation
Part 3: Text Augmentation
8
Chapter 5: Text Augmentation
Chapter 5: Text Augmentation
Character augmenting
Word augmenting
Sentence augmentation
Text augmentation libraries
Real-world text datasets
Reinforcing learning through Python Notebook
Summary
9
Chapter 6: Text Augmentation with Machine Learning
Chapter 6: Text Augmentation with Machine Learning
Machine learning models
Word augmenting
Sentence augmenting
Real-world NLP datasets
Reinforcing your learning through the Python Notebook
Summary
10
Part 4: Audio Data Augmentation
Part 4: Audio Data Augmentation
11
Chapter 7: Audio Data Augmentation
Chapter 7: Audio Data Augmentation
Standard audio augmentation techniques
Filters
Audio augmentation libraries
Real-world audio datasets
Reinforcing your learning
Summary
12
Chapter 8: Audio Data Augmentation with Spectrogram
Chapter 8: Audio Data Augmentation with Spectrogram
Initializing and downloading
Audio Spectrogram
Various Spectrogram formats
Mel-spectrogram and Chroma STFT plots
Spectrogram augmentation
Spectrogram images
Summary
13
Part 5: Tabular Data Augmentation
Part 5: Tabular Data Augmentation
14
Chapter 9: Tabular Data Augmentation
Chapter 9: Tabular Data Augmentation
Tabular augmentation libraries
Augmentation categories
Real-world tabular datasets
Exploring and visualizing tabular data
Transforming augmentation
Interaction augmentation
Mapping augmentation
Extraction augmentation
Summary
15
Index
Index
Why subscribe?
16
Other Books You May Enjoy
Other Books You May Enjoy
Packt is searching for authors like you
Share your thoughts
Download a free PDF copy of this book

Summary

In this chapter, you learned that data augmentation is essential for achieving higher accuracy prediction in DL and generative AI. Data augmentation is an economical option for extending a dataset without the difficulty of purchasing and labeling new data.

The four input data types are image, text, audio, and tabular. Each data type faces different challenges, techniques, and limitations. Furthermore, the dataset dictates which functions and parameters are suitable. For example, people’s faces and aerial photographs are image datasets, but you can’t expand the data by vertically flipping people’s images; however, you can vertically flip aerial photos.

In the second part of this chapter, you used Python notebooks to reinforce your learning of these augmentation concepts. This involved selecting a Python Notebook as the default IDE to access a cloud-based platform, such as Google Colab or Kaggle, or installing the Python Notebook locally on your laptop.

The Programming styles section lay the foundation for the Python Notebook’s structure. It touched on GitHub as a form of source control, using base classes, extending base classes, long library function names, exporting to Python, and introducing Pluto.

This chapter laid the foundation with Pluto as the main object. Pluto does not start with complete data augmentation functions – he begins with a minimum structure, and as he learns new data augmentation concepts and techniques from chapter to chapter, he will add new methods to his arsenal.

By the end of this book, Pluto and you will learn techniques regarding how to augment image, text, audio, and tabular data. In other words, you will learn how to write a powerful image, text, audio, and tabular augmentation class from scratch using real-world data, which you can reuse in future data augmentation projects.

Throughout this chapter, there were fun facts and fun challenges. Pluto hopes you will take advantage of what’s been provided and expand your experience beyond the scope of this chapter.

In Chapter 2, Biases in Data Augmentation, Pluto and you will explore how data augmentation can increase biases. Using data biases as a guiding principle to data augmentation is an often-overlooked technique.

Previous Section
End of Chapter 2
Next Chapter