This class was learned from 204 images of Stonehenge. The visualizations below show the maximally activated representations of what makes Stonehenge look like Stonehenge. Each image begins with a randomly-seeded noise image, which leads to a slightly different class representation. Below are 12 activations created from 12 random noise images.
- Images used for training: 204
- Image sources: Google (83) , Flickr (76)
- Bounding boxes and URLs: stonehenge.json