EuroNet / Döner / Version 1
Class: Döner

Below are 40 iterations of showing how the neural model learned to represent this class. The visualizations below show the maximally activated representations of what makes Döner look like Döner

Data Sources
  • Images used for training: 145
  • Image sources: Google (44) , Flickr (101)
  • Bouding boxes and URLs: doner.json