EuroNet / Fish and Chips
Class: Fish and Chips

This class was learned from 164 images of Fish and Chips. The visualizations below show the maximally activated representations of what makes Fish and Chips look like Fish and Chips. 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: 164
  • Image sources: Google (127) , Flickr (31)
  • Bounding boxes and URLs: fish-and-chips.json