Image Classification and CNN
Building a CNN Classifier with PyTorch: Part 1
Building a CNN Classifier with PyTorch: Part 2
Introduction to DDP with PyTorch
Single Node Multi-GPU Training with torchrun
Multi-node Distributed Training with PyTorch
Lab Setup

Data Augmentation

What if our CNN model overfits the training dataset, and we are not able to collect more data? A simple solution is to just “make up” more data based on the existing training data. This is the idea behind data augmentation. Every time we sample an image from the dataset, we randomly perform some operations on them. For instance, shift, rotate, horizontal and vertical flip, clip, etc. PyTorch has implemented such operations for us.

Back
 
Next
© Chishiki-AI  |   Cornell University    |   Center for Advanced Computing    |   Copyright Statement    |   Access Statement
CVW material development is supported by NSF OAC awards 1854828, 2321040, 2323116 (UT Austin) and 2005506 (Indiana University)