Who's a good dog? Who likes ear scratches? Well, it seems those fancy deep neural networks don't have *all* the answers. However, maybe they can answer that ubiquitous question we all ask when meeting a four-legged stranger: what kind of good pup is that?

In this playground competition, you are provided a strictly canine subset of [ImageNet][2] in order to practice fine-grained image categorization. How well you can tell your Norfolk Terriers from your Norwich Terriers? With 120 breeds of dogs and a limited number training images per class, you might find the problem more, err, ruff than you anticipated.

![Border collies][1]


### Acknowledgments

We extend our gratitude to the creators of the [Stanford Dogs Dataset][3] for making this competition possible: Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, and Fei-Fei Li.


  [1]: https://storage.googleapis.com/kaggle-media/competitions/kaggle/3333/media/border_collies.png
  [2]: https://www.kaggle.com/c/imagenet-object-detection-challenge
  [3]: http://vision.stanford.edu/aditya86/ImageNetDogs/