This class was learned from 150 images of Moussaka. The visualizations below show the maximally activated representations of what makes Moussaka look like Moussaka. 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: 150
- Image sources: Google (109) , Flickr (35)
- Bounding boxes and URLs: moussaka.json