The dataset consists of 2 folders: 'train' and 'test'. The folder 'train' is a labelled dataset and consists of 2 sub-folders: 'cracked' and 'uncracked'. The sub-folder 'cracked' consists of a total of 7501 images containing cracks, while the 'uncracked' sub-folder contains 7467 images with no cracks. All images are of the ‘.jpg’ format.
The ‘test’ folder consists of the test dataset images. There are a total of 2000 images in this folder (all ‘.jpg’ files). These images are unlabelled i.e., the labels are not provided, whether they contain cracks or not. The objective of this challenge is to predict the class of each of these test images. The class can be either ‘cracked’ or ‘uncracked’. The filenames of these test images are given as 1.jpg, 2.jpg, 3.jpg, …, 2000.jpg.