Saturday, December 25, 2021

What training data look like in image classification?

 What does training data look like in image classification tasks?

Images are separated into train, valid folders.

Within each folder, images are organized by the numeric value corresponding to their class name e.g.0,1,2. ... usually starting from 0 to the number of classes minus 1 when it is zero-indexed. Else it starts at 1. 

This is what the oxford flower dataset looks like

No comments:

Post a Comment