I've updated the Keras deep dream example to be closer to the original, but the hyperparameters still need tweaking https://github.com/fchollet/keras/blob/master/examples/deep_dream.py …pic.twitter.com/MhfewcVG7N
-
The reason deep dream does not generate visually interesting results is because it uses a network trained on ImageNet (dogs and birds...)
Training e.g. an artist classification network on thousands of paintings would allow to generate much more artistic and creative dreams
-
-
Instead of infinite dog eyes
-
we need a fauna classifier and the eye of the tiger cc
@katyperry - Show replies
New conversation -
-
-
"artistic & creative" in a very conventional sense tho. the greatest representational leaps won't fit historical interpretation of the terms
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It still looks cool tho.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
soooo something like https://github.com/metmuseum/openaccess …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.