Quick reply offline. You need to assist the hyper parameter. The second later cost is very close to 0 . So maybe you don't need a third layer?
If you want to investigate more, in Theano web site, there is a page on finding the cause of nan. Le 19 janv. 2017 05:05, "Sayantan Ghosh" <sayantanghosh...@gmail.com> a écrit : > I am new to both deep learning and theano. I am following the > deeplearning.net dbn tutorial to build a dbn. But when I am feeding the > data to it, at the second pretraining stage I am getting 'nan' as cost. How > to get rid of this? > > The complete file set is uploaded https://drive.google.com/open?id=0B02Uz- > muAJWWTk5WTXpvTGF0SUk > > I run the DBN.py file under the ova_svm folder. > > -- > > --- > You received this message because you are subscribed to the Google Groups > "theano-users" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to theano-users+unsubscr...@googlegroups.com. > For more options, visit https://groups.google.com/d/optout. > -- --- You received this message because you are subscribed to the Google Groups "theano-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to theano-users+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
