This class was learned from 146 images of Fondue. The visualizations below show the maximally activated representations of what makes Fondue look like Fondue. 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: 146
- Image sources: Google (89) , Flickr (43)
- Bounding boxes and URLs: fondue.json