computer vision - Google Inceptionism: obtain images by class -


in famous google inceptionism article, http://googleresearch.blogspot.jp/2015/06/inceptionism-going-deeper-into-neural.html show images obtained each class, such banana or ant. want same other datasets.

the article describe how obtained, feel explanation insufficient.

there's related code https://github.com/google/deepdream/blob/master/dream.ipynb

but produce random dreamy image, rather specifying class , learn looks in network, shown in article above.

could give more concrete overview, or code/tutorial on how generate images specific class? (preferably assuming caffe framework)

i think this code starting point reproduce images google team published. procedure looks clear:

  1. start pure noise image , class (say "cat")
  2. perform forward pass , backpropagate error wrt imposed class label
  3. update initial image gradient computed @ data layer

there tricks involved, can found in original paper.

it seems main difference google folks tried more "realistic" image:

by itself, doesn’t work well, if impose prior constraint image should have similar statistics natural images, such neighboring pixels needing correlated.


Comments

Popular posts from this blog

html - Outlook 2010 Anchor (url/address/link) -

javascript - Why does running this loop 9 times take 100x longer than running it 8 times? -

Getting gateway time-out Rails app with Nginx + Puma running on Digital Ocean -