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

Geometric transformations

Geometric transformation alters the photo’s geometry, which is done by flipping along the X-axis or Y-axis, cropping, padding, rotating, warping, and translation. Complex augmentation uses these base photo-altering techniques. While working with geometric transformations, the distortion magnitude has to be kept to a safe level, depending on the image topic. Thus, no general formula governing geometric transformation applies to all photos. In the second half of this chapter, the Python coding section, you and Pluto will download real-world image datasets to define the safe level for each image set.

The following techniques are not mutually exclusive. You can combine horizontal flipping with cropping, resizing, padding, rotating, or any combination thereof. The one constraint is the safe level for distortion.

In particular, you will learn the following techniques:

  • Flipping
  • Cropping
  • Resizing
  • Padding
  • Rotating
  • Translation...