This class was learned from 10 images of Parmesan. The visualizations below show the maximally activated representations of what makes Parmesan look like Parmesan. 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: 10
- Image sources: Google (0) , Flickr (9)
- Bounding boxes and URLs: parmesan.json