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

Spectrogram images

Fundamentally, audio data is time-series data. Thus AI uses a time-series algorithm, such as the autoregressive integrated moving average (ARIMA) or exponential smoothing (ES) algorithm for audio classification. However, there is a better method. You use the Spectrogram as an image representing the audio sound, not the time-series numerical array, for input. Using images as the input data, you can leverage the robust neural network algorithm to classify audio more accurately.

Strictly speaking, this topic does not directly pertain to new audio augmentation techniques. Still, it is an essential topic for data scientists to understand. However, Pluto will not write Python code for building a neural network model using Spectrograms as input.

Deep learning image classification, also known as the machine learning model that uses the artificial neural networks algorithm, achieved an unprecedented accuracy level that exceeds 98% accuracy recently. Many AI scientists...