Re: [theano-users] Taking softmax within the step function in RNN

. Cheers, Mohammad. On Wednesday, November 9, 2016 at 12:09:12 AM UTC+10:30, nouiz wrote: > > If you want a chase to get more help, tell what you expected and what you > got. > > Fred > > Le 8 nov. 2016 05:53, "Mohammad Najafi" <najaf...@gmail.com > > a é

[theano-users] Taking softmax within the step function in RNN

Hi, I want the softmax of the RNN output, to be computed within the step function, like below: def step(x_t, h_tm1): h_t = self.activation(T.dot(x_t, self.W_in) + T.dot(h_tm1, self.W) + self.bh) y_t = T.dot(h_t, self.W_out) + self.by y_t = T.nnet.softmax(y_t) return h_t, y_t