This class was learned from 29 images of Ftira. The visualizations below show the maximally activated representations of what makes Ftira look like Ftira. 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: 29
- Image sources: Google (25) , Flickr (2)
- Bounding boxes and URLs: ftira.json