Image Augmentation: A Practical Guide to Prevent Overfitting in Computer Vision

This talk starts with demos of the basic standard transforms using the albumentations Python package, and work up to some more advanced strategies like CutMix and mixup.
Course info
Level
Beginner
Updated
Oct 19, 2020
Duration
28m
Table of contents
Image Augmentation: A Practical Guide to Prevent Overfitting in Computer Vision
Description
Course info
Level
Beginner
Updated
Oct 19, 2020
Duration
28m
Description

For machine learning models, we all know more data is better. For convolutional neural networks, image augmentation provides a straightforward way to expand your training dataset, by applying simple transformations to the images you already have. In this talk I'll start by demoing the basic standard transforms using the albumentations python package, and work up to some more advanced strategies like CutMix and mixup. I will also discuss some findings of the RxRx1 kaggle competition that Recursion ran last summer, and how this demonstrated the power of these techniques when applied to our cellular image data.

About the author
About the author

Pluralsight LIVE is the ultimate gathering of industry experts, business leaders and change-makers. As Pluralsight's annual user conference, LIVE is where technologists from around the world come together to look into the future and prepare for the challenges and opportunities ahead.

More from the author
More courses by Pluralsight LIVE