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

Real-world segmentation datasets

The Kaggle website is an online community platform for data scientists and ML devotees. It contains thousands of real-world datasets, as mentioned in Chapters 1, 2, and 3.

When searching for image segmentation datasets, Pluto found about 500 useable real-world segmentation datasets. The topics range from self-driving automobiles and medicine to micro-fossils. Pluto picked two segmentation datasets from popular market segments.

The other consideration is that the image type must be easy to work with in the Albumentations library. Pluto uses the PIL and NumPy libraries to read and convert the photos into a three-dimensional array. The original image’s shape is (width, height, and depth), where depth is usually equal to three. The mask image’s shape is (width, height), where the value is 0, 1, 2, and so on up to the number of labels.

Fun fact

The PIL library can read image formats such as .jpg, .gif, .tiff, .png, and about 50...