Stanford Cars Dataset is an image dataset containing 196 types of cars. It is mainly used for image classification. It has a total of 16,185 images, of which 8,144 are training images and 8,041 are test images. The number of images in each category is equal. The classification is based on car brand, model and year.

This dataset was released by Stanford University – Artificial Intelligence Laboratory in 2013, and the related paper is “3D Object Representations for Fine-Grained Categorization”.