This class was learned from 75 images of Gouda. The visualizations below show the maximally activated representations of what makes Gouda look like Gouda. 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: 75
- Image sources: Google (57) , Flickr (4)
- Bounding boxes and URLs: gouda.json