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)
1
Part 1: Data Augmentation
4
Part 2: Image Augmentation
7
Part 3: Text Augmentation
10
Part 4: Audio Data Augmentation
13
Part 5: Tabular Data Augmentation

Spectrogram augmentation

Pluto will reuse most of the wrapper functions from Chapter 7. You can reread the previous chapter if the following code seems challenging. Pluto will shorten his explanation of the wrapper functions because he assumes you are an expert at writing audio augmentation wrapper functions.

Audio Spectrogram, Mel-spectrogram, Chroma STFT, and Waveform charts take the returned amplitude data and sampling rate from the Librosa load() function reading an audio file. There is an additional transformation of the amplitude data, but they serve the same goal of visualizing the sound wave and frequencies.

After reviewing many scholarly published papers, Pluto concluded that the audio augmentation techniques in Chapter 7 apply equally well to the audio Spectrogram, Mel-spectrogram, and Chroma STFT. In particular, he referred to the scholarly paper, Audio Augmentation for Speech Recognition by Tom Ko, Vijayaditya Peddinti, Daniel Povey, and Sanjeev Khudanpur, published...