This class was learned from 171 images of Gondola. The visualizations below show the maximally activated representations of what makes Gondola look like Gondola. 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: 171
- Image sources: Google (55) , Flickr (93)
- Bounding boxes and URLs: gondola.json