This class was learned from 130 images of Pierogi. The visualizations below show the maximally activated representations of what makes Pierogi look like Pierogi. 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: 130
- Image sources: Google (65) , Flickr (37)
- Bounding boxes and URLs: pierogi.json