PyTorch Recipes: A Problem-Solution Approach to Build, Train and Deploy Neural Network Models

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2023

P. MishraPyTorch Recipeshttps://doi.org/10.1007/978-1-4842-8925-9_9

9. Data Augmentation, Feature Engineering, and Extractions for Image and Audio

Pradeepta Mishra¹  

(1)

Bangalore, Karnataka, India

 

In an audio classification model, you want the deep learning algorithm to learn sounds and predict a category. Similarly, in image classification, you want the deep learning model to remember the images, learn the patterns from the images, and classify new images into various categories that the learning algorithm has been trained on. In sound classification, you typically start by taking the audio files as inputs and convert them into something called a spectogram ...