Skip main navigation

Practical: Data augmentation

A practical article on data augmentation and cross-validation with an image classifier
An image of a Daffodil flower rotated at a random angle anti-clockwise
This week, among other things, we have looked at expanding dataset size using data augmentation, and the use of cross-validation during model evaluation.

In this week’s practical, we will demonstrate some simple data augmentation techniques using the flower dataset, as well as how to use cross-validation on the augmented image dataset.

All the instructions are in the attached pdf in the Downloads section below.

We would encourage you to type the code in as you follow the practical through, to get in the practice of writing your own code.

However, if you want it, the sample script containg all the code used in the practical can be downloaded from our Github repository at

Please let us know how you get on in the comments below.

This article is from the free online

Machine Learning for Image Data

Created by
FutureLearn - Learning For Life

Reach your personal and professional goals

Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.

Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.

Start Learning now