This class was learned from 87 images of Sauerkraut. The visualizations below show the maximally activated representations of what makes Sauerkraut look like Sauerkraut. 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: 87
- Image sources: Google (53) , Flickr (26)
- Bounding boxes and URLs: sauerkraut.json