This class was learned from 110 images of Mozzarella. The visualizations below show the maximally activated representations of what makes Mozzarella look like Mozzarella. 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: 110
- Image sources: Google (67) , Flickr (10)
- Bounding boxes and URLs: mozzarella.json