This class was learned from 45 images of Guillotine. The visualizations below show the maximally activated representations of what makes Guillotine look like Guillotine. 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: 45
- Image sources: Google (35) , Flickr (4)
- Bounding boxes and URLs: guillotine.json