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

Image Augmentation for Classification

Image augmentation in machine learning (ML) is a stable diet for increasing prediction accuracy, especially for the image classification domain. The causality logic is linear, meaning the more robust the data input, the higher the forecast accuracy.

Deep learning (DL) is a subset of ML that uses artificial neural networks to learn patterns and forecast based on the input data. Unlike traditional ML algorithms, which depend on programmer coding and rules to analyze data, DL algorithms automatically learn, solve, and categorize the relationship between data and labels. Thus, expanding the datasets directly impacts DL predictions on new insights that the model has not seen in the training data.

DL algorithms are designed to mimic the human brain, with layers of neurons that process information and pass it on to the next layer. Each layer of neurons learns to extract increasingly complex features from the input data, allowing the network to identify...