This class was learned from 94 images of Gorgonzola. The visualizations below show the maximally activated representations of what makes Gorgonzola look like Gorgonzola. 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: 94
- Image sources: Google (49) , Flickr (32)
- Bounding boxes and URLs: gorgonzola.json