NOTE: This is a pared down version of the original RPS dataset created by Julien de la Bruère-Terreault, hosted at https://www.kaggle.com/drgfreeman/rockpaperscissors. It contains 900 images instead of the original 2188 images so that it can be used with the Firebase Spark plan.

The information from the original README file follows:

AUTHOR: Julien de la Bruère-Terreault (drgfreeman@tuta.io)

LICENSE: CC-BY-SA 4.0

DESCRIPTION: This dataset contains images of hand gestures from the Rock-Paper-Scissors game. The images were captured as part of a hobby project where I developped a Rock-Paper-Scissors game using computer vision and machine learning on the Raspberry Pi (https://github.com/DrGFreeman/rps-cv)

CONTENTS: The dataset contains a total of 2188 images corresponding to the 'Rock' (726 images), 'Paper' (710 images) and 'Scissors' (752 images) hand gestures of the Rock-Paper-Scissors game. All image are taken on a green background with relatively consistent ligithing and white balance.

FORMAT: All images are RGB images of 300 pixels wide by 200 pixels high in .png format. The images are separated in three sub-folders named 'rock', 'paper' and 'scissors' according to their respective class.