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

Reinforcing your learning

The same concepts for classification image transformations apply to segmentation image transformations. Here, Pluto reuses or slightly hacks the wrapper functions in Chapter 3. In particular, Pluto hacks the following methods for segmentation:

  • Horizontal flip
  • Vertical flip
  • Rotating
  • Random resizing and cropping
  • Transpose
  • Lighting
  • FancyPCA

Fun fact

You can’t complete or understand this chapter unless you have read Chapter 3. This is because Pluto reuses or slightly modifies the existing image augmentation wrapper functions.

Pluto chose these filters because the Albumentations library marked them as safe for segmentation. So, let’s start with horizontal flip.

Horizontal flip

Pluto demonstrated horizontal flip using the PIL library in Chapter 3 because the code is easy to understand. Thus, he will hack draw_image_flip_pil() into the draw_image_flip_pil_segmen() function. The transformation code is...