DeepAlignmentNetwork icon indicating copy to clipboard operation
DeepAlignmentNetwork copied to clipboard

Published 20 hours ago • verified publisher icon MarekKowalski

why did you split your network into two stages to train? what is the different between all to train and split train?

Open dami2014 opened this issue 7 years ago • 1 comments

dami2014 avatar Jul 19 '18 07:07 dami2014

The stages were separated to allow the first stage to learn fully before the second stage is added. Thanks to this approach the second stage doesn't start lerning before the first stage is able to make sensible predictions.

Marek

MarekKowalski avatar Jul 25 '18 00:07 MarekKowalski