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


Audio augmentation is challenging to explain in a book format. Still, we gain a deeper understanding of audio amplitude, frequency, and sampling rate with additional visualization techniques, such as the audio Spectrogram, Mel-spectrogram, and Chroma STFT. Furthermore, in the Python Notebook, you can listen to the before-and-after effects of the audio augmentation.

Compared to the previous chapter, Waveform graphs show the amplitude of a signal over time, giving an understanding of its shape and structure. Spectrogram graphs show a visual representation of the frequencies of a signal over time, providing a deeper insight into the harmonic content of the sound.

An Audio Spectrogram comes in many variations, whether color mapping, window filtering, spectrum sides, magnitude mode, or frequency scale, among many more in the underlying Matplotlib specgram() function. Pluto uses Python code in wrapper functions on a few Spectrogram types. The majority of Spectrogram variations...