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 Spectrogram

Before dissecting the Spectrogram, let’s review the fundamental differences between a Spectrogram and a Waveform plot. The Spectrogram graphs show the frequency components of a sound signal over time, focusing on frequency and intensity. In contrast, the Waveforms concentrate on the timing and amplitude of sounds. The difference is in the visual representation of the sound wave. The underlying data representation and the transformation methods are the same.

An audio Spectrogram is another visual representation of a sound wave, and you saw the Waveform graph in Chapter 7. The _draw_spectrogram() helper method uses the Librosa library to import the audio file and convert it into an amplitude data one-dimensional array and a sampling rate in Hz. The next step is to use the Matplotlib library to draw the Spectrogram plot. Likewise, Pluto takes the output from the Librosa library function and uses the Matplotlib function to draw the fancy blue and yellow Waveform...