This class was learned from 88 images of Cheddar. The visualizations below show the maximally activated representations of what makes Cheddar look like Cheddar. 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: 88
- Image sources: Google (67) , Flickr (5)
- Bounding boxes and URLs: cheddar.json