[incubator-mxnet] branch master updated: Fix RNN doc (#10348)

[zh...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

zhasheng pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git


The following commit(s) were added to refs/heads/master by this push:
     new 3f9f871  Fix RNN doc (#10348)
3f9f871 is described below

commit 3f9f871b774e9537a00080853ac0d21166a58767
Author: Xingjian Shi <xs...@ust.hk>
AuthorDate: Fri Mar 30 22:36:50 2018 -0700

    Fix RNN doc (#10348)
    
    * fix doc
    
    * fix
---
 python/mxnet/gluon/rnn/rnn_layer.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/python/mxnet/gluon/rnn/rnn_layer.py b/python/mxnet/gluon/rnn/rnn_layer.py
index c82e953..2aaaeb2 100644
--- a/python/mxnet/gluon/rnn/rnn_layer.py
+++ b/python/mxnet/gluon/rnn/rnn_layer.py
@@ -244,8 +244,8 @@ class RNN(_RNNLayer):
     .. math::
         h_t = \tanh(w_{ih} * x_t + b_{ih}  +  w_{hh} * h_{(t-1)} + b_{hh})
 
-    where :math:`h_t` is the hidden state at time `t`, and :math:`x_t` is the hidden
-    state of the previous layer at time `t` or :math:`input_t` for the first layer.
+    where :math:`h_t` is the hidden state at time `t`, and :math:`x_t` is the output
+    of the previous layer at time `t` or :math:`input_t` for the first layer.
     If nonlinearity='relu', then `ReLU` is used instead of `tanh`.
 
     Parameters

-- 
To stop receiving notification emails like this one, please contact
zhasheng@apache.org.