Giters

dennybritz / rnn-tutorial-rnnlm

Recurrent Neural Network Tutorial, Part 2 - Implementing a RNN in Python and Theano

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Why the timestep is not used in the forward_propagation

Tongjilibo opened this issue · comments

commented

When i use lstm in keras or tensorflow, they have different data strctures. When i compared this tutorial with keras, i found the 'timestep' is only used in the backward_propagation, but not in the forward_propagation is this right?