This class was learned from 173 images of Neuschwanstein. The visualizations below show the maximally activated representations of what makes Neuschwanstein look like Neuschwanstein. 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: 173
- Image sources: Google (92) , Flickr (78)
- Bounding boxes and URLs: neuschwanstein-castle.json