This class was learned from 108 images of Fiddle. The visualizations below show the maximally activated representations of what makes Fiddle look like Fiddle. 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: 108
- Image sources: Google (38) , Flickr (36)
- Bounding boxes and URLs: fiddle.json