Re:Deep Dreams with Caffe
by wodenokoto on Thursday July 02, 2015 @12:02PM
(#9819762)
I imagine the chance of an input that would result in zero confidence in all output nodes is damn near zero.
There will basically always be an output nose with the highest confidence, no matter how low.
Perhaps this is working entirely differently and I'm thinking too much in the classical computer vision realm. Would love some explanation though.