This class was learned from 74 images of Alhambra. The visualizations below show the maximally activated representations of what makes Alhambra look like Alhambra. 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: 74
- Image sources: Google (63) , Flickr (0)
- Bounding boxes and URLs: alhambra.json