This dataset was originally created to colorize Charles Dickens’ illustrations. Due to a lack of data, however, the scope of this dataset has been expanded to all nineteenth century illustrations. Colorful images from the nineteenth century were selected to be used in the dataset, which were converted to black and white images for training data. The Victorian400 dataset is small, so it will be good for data scientists who need to test cGAN/GAN models. This dataset contains three different folders: original, resized, and gray. Images in the ‘original’ folder were curated for significant features, such as faces and bodies. In the 'resized' folder, the original images were resized to fit the 256*256 dimensions needed for the process of deep learning. Based on the resized images, I created the 'gray' folder, which contains black and white images converted from the colorful resized images.

Resource Fields

Project Open Data Required Fields (version 1.1)

Project Open Data Additional Fields (version 1.0)

Project Open Data Required-if-Applicable Fields (version 1.1)