This class was learned from 128 images of Camembert. The visualizations below show the maximally activated representations of what makes Camembert look like Camembert. 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: 128
- Image sources: Google (82) , Flickr (28)
- Bounding boxes and URLs: camembert.json