Hi. I would like to use softmax in the last layer of my nnet, but specifically, I would like to use it after a fully connected layer. So my question are:
- he output of the softmax (y) is what I have to pass to the classifier, isn't it? - And the W, x and b are the parameters of the fully connected layer, where x are samples? I hope I have explained myself correctly. Thank you for your help. El miércoles, 27 de agosto de 2014, 6:06:41 (UTC+2), nouiz escribió: > > Here is the doc: > > > http://deeplearning.net/software/theano/library/tensor/nnet/nnet.html#tensor.nnet.softmax > > If that don't answer your questions, tell us what else you want to know. > > Fred > > > On Mon, Aug 25, 2014 at 12:31 PM, Divyansh Khanna <[email protected] > <javascript:>> wrote: > >> Hi >> >> I have been trying to work with theano. Can anybody clearly explain how >> does the tensor.nnet.softmax works and is it tensor specific ? >> >> Thanx. >> >> -- >> >> --- >> 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 [email protected] <javascript:>. >> 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 [email protected]. For more options, visit https://groups.google.com/d/optout.
