You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by jx...@apache.org on 2017/07/31 02:57:29 UTC

[incubator-mxnet] branch master updated: Fixes for gluon RNN [WIP] (#7258)

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

jxie 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 1ed5f9f  Fixes for gluon RNN [WIP] (#7258)
1ed5f9f is described below

commit 1ed5f9fea5ba399bfdf3e3808123f1b153397c44
Author: Leonard Lausen <le...@lausen.nl>
AuthorDate: Mon Jul 31 11:57:27 2017 +0900

    Fixes for gluon RNN [WIP] (#7258)
    
    * Fix documentation on recurrent state shape for gluon
    
    * Fix state info for gluon rnn_layers
    
    * Revert "Fix state info for gluon rnn_layers"
    
    This reverts commit 5f791d6e8b643f08dfde6475bef396d9abddb875.
---
 python/mxnet/gluon/rnn/rnn_layer.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/python/mxnet/gluon/rnn/rnn_layer.py b/python/mxnet/gluon/rnn/rnn_layer.py
index a22cb01..d567369 100644
--- a/python/mxnet/gluon/rnn/rnn_layer.py
+++ b/python/mxnet/gluon/rnn/rnn_layer.py
@@ -268,7 +268,7 @@ class RNN(_RNNLayer):
     Recurrent state shape:
         The recurrent state's shape is `(num_layers, batch_size, num_hidden)`.
         If `bidirectional` is True, state shape will instead be
-        `(num_layers, batch_size, 2*num_hidden)`
+        `(2*num_layers, batch_size, num_hidden)`
 
 
     Examples
@@ -366,7 +366,7 @@ class LSTM(_RNNLayer):
         The recurrent state is a list of two NDArrays. Both has shape
         `(num_layers, batch_size, num_hidden)`.
         If `bidirectional` is True, state shape will instead be
-        `(num_layers, batch_size, 2*num_hidden)`.
+        `(2*num_layers, batch_size, num_hidden)`.
 
 
     Examples
@@ -460,7 +460,7 @@ class GRU(_RNNLayer):
     Recurrent state shape:
         The recurrent state's shape is `(num_layers, batch_size, num_hidden)`.
         If `bidirectional` is True, state shape will instead be
-        `(num_layers, batch_size, 2*num_hidden)`
+        `(2*num_layers, batch_size, num_hidden)`
 
 
     Examples

-- 
To stop receiving notification emails like this one, please contact
['"commits@mxnet.apache.org" <co...@mxnet.apache.org>'].