Skip to content

Instantly share code, notes, and snippets.

View nickuntitled's full-sized avatar

Kittisak nickuntitled

View GitHub Profile
@nickuntitled
nickuntitled / separation_dataaugmentation_technique.md
Created September 9, 2023 17:53
This file contains the approaches to modify data augmentation processes.

Modification of Data Augmentation to be one step or two steps

Data augmentation is the process to increase the diversity of dataset by using synthetic data generation. Normally, when using data augmentation, we have to sequentially augment the image from the datasets. However, this method gives the unaltered image with one figure chances.

From the above reason, there is a modification of data augmentation into two methods.

One step data augmentation

This approach is to modify the data augmentation processes (Figure 1) to have

  1. 50% chance to get the unmodified image