This class was learned from 175 images of Tulpen. The visualizations below show the maximally activated representations of what makes Tulpen look like Tulpen. 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: 175
- Image sources: Google (51) , Flickr (89)
- Bounding boxes and URLs: tulips.json