Building a CNN Classifier with PyTorch: Part 1
Krishna Kumar
The University of Texas at Austin, Chishiki-AI
5/2024 (original)
In this tutorial, we will walk through the basic components of building a CNN classifier with PyTorch. We will use a DesignSafe dataset from Hurricane Harvey, a category 4 hurricane that hit Texas in August of 2017 and resulted in catastrophic flooding to the Houston metropolitan area. The data set is specifically focused on image classification of homes according to the amount of damage the home received. All images of homes are labeled as C0, C2, or C4 respectively for low, medium or high damage.

PyTorch is a popular machine learning library for building deep learning models developed by Facebook. The basics of building a CNN model with PyTorch can be broken down into the following components:
Dataset Loaders and Transforms
Building the Neural Network
Training the Neural Network
CVW material development is supported by NSF OAC awards 1854828, 2321040, 2323116 (UT Austin) and 2005506 (Indiana University)