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


Text augmentation with machine learning (ML) is an advanced technique. We used a pre-trained ML model to create additional training NLP data.

After inputting the first three paragraphs, the T5 NLP ML engine wrote the preceding summary for this chapter. It is perfect and illustrates the spirit of this chapter. Thus, Pluto has kept it as-is.

In addition, we discussed 14 NLP ML models and four word augmentation methods. They were Word2Vec, BERT, RoBERTa, and back translation.

Pluto demonstrated that BERT and RoBERTa are as good as human writers. The augmented text is not just merely appropriate but inspirational, such as replacing it was the age of foolishness with death was the age of love or it was the epoch of belief with it was the age of youth.

For the back translation method, Pluto used the Facebook or Meta AI NLP model to translate to German and Russian and back to English.

For sentence augmentation, Pluto dazzled with the accuracy of the T5 NLP ML engine...