This class was learned from 145 images of Döner. The visualizations below show the maximally activated representations of what makes Döner look like Döner. 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: 145
- Image sources: Google (44) , Flickr (101)
- Bounding boxes and URLs: doner.json