EuroNet / Sorrel soup
Class: Sorrel soup

This class was learned from 134 images of Sorrel soup. The visualizations below show the maximally activated representations of what makes Sorrel soup look like Sorrel soup. 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.

Data Sources
  • Images used for training: 134
  • Image sources: Google (53) , Flickr (57)
  • Bounding boxes and URLs: sorrel-soup.json