This class was learned from 88 images of Versailles. The visualizations below show the maximally activated representations of what makes Versailles look like Versailles. 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: 88
- Image sources: Google (41) , Flickr (26)
- Bounding boxes and URLs: versailles-mirror-room.json