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


As we saw from the beginning, audio augmentation is a challenging topic without hearing the audio recording in question, but we can visualize the techniques’ effect using Waveform graphs and zoom-in charts. Still, there is no substitution for listening to the before and after augmentation recordings. You have access to the Python Notebook with the complete code and audio button to play the augmented and original recordings.

First, we discussed the theories and concepts of an audio file. The three fundamental components of an audio file are amplitude, frequency, and sampling rate. The measurements of unit for frequency are Hertz (Hz) and Kilohertz (kHz). Pitch is similar to frequency, but the unit of measurement is the decibel (dB). Similarly, bit rate and bit depth are other forms expressing the sampling rate.

Next, we explained the standard audio augmentation techniques. The three essentials are time stretching, time shifting, and pitch scaling. The others are...