This class was learned from 227 images of Beret. The visualizations below show the maximally activated representations of what makes Beret look like Beret. 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: 227
- Image sources: Google (132) , Flickr (95)
- Bounding boxes and URLs: barret.json