Context

This is the Stanford car dataset. The difference is the .zip file contains all the images with this structure:
 -> train -> 2012 Tesla Model S
               -> 2012 BMW M3 coupe
               …
 -> test  -> 2012 Tesla Model S
              -> 2012 BMW M3 coupe
              …

Content

The Cars dataset contains 16,185 images of 196 classes of cars. The data is split into 8,144 training images and 8,041 testing images, where each class has been split roughly in a 50-50 split. Classes are typically at the level of Make, Model, Year, e.g. 2012 Tesla Model S or 2012 BMW M3 coupe.

Acknowledgements

see this paper