You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by ha...@apache.org on 2018/01/04 18:01:33 UTC

[incubator-mxnet] branch master updated: fix w&d (#9303)

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

haibin 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 5e587e5  fix w&d (#9303)
5e587e5 is described below

commit 5e587e59dbefd7f0e399791c4ecedead0b1e46ce
Author: Ziyue Huang <zy...@gmail.com>
AuthorDate: Fri Jan 5 02:01:30 2018 +0800

    fix w&d (#9303)
---
 example/sparse/wide_deep/README.md | 2 +-
 example/sparse/wide_deep/model.py  | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/example/sparse/wide_deep/README.md b/example/sparse/wide_deep/README.md
index a538106..3df5e42 100644
--- a/example/sparse/wide_deep/README.md
+++ b/example/sparse/wide_deep/README.md
@@ -4,4 +4,4 @@ The example demonstrates how to train [wide and deep model](https://arxiv.org/ab
 
 The final accuracy should be around 85%.
 
-- `python wide_deep_classification.py`
+- `python train.py`
diff --git a/example/sparse/wide_deep/model.py b/example/sparse/wide_deep/model.py
index e8ba531..b907455 100644
--- a/example/sparse/wide_deep/model.py
+++ b/example/sparse/wide_deep/model.py
@@ -49,9 +49,9 @@ def wide_deep_model(num_linear_features, num_embed_features, num_cont_features,
 
     hidden = mx.symbol.concat(*features, dim=1)
     hidden = mx.symbol.FullyConnected(data=hidden, num_hidden=hidden_units[1])
-    hideen = mx.symbol.Activation(data=hidden, act_type='relu')
+    hidden = mx.symbol.Activation(data=hidden, act_type='relu')
     hidden = mx.symbol.FullyConnected(data=hidden, num_hidden=hidden_units[2])
-    hideen = mx.symbol.Activation(data=hidden, act_type='relu')
+    hidden = mx.symbol.Activation(data=hidden, act_type='relu')
     deep_out = mx.symbol.FullyConnected(data=hidden, num_hidden=2)
 
     out = mx.symbol.SoftmaxOutput(linear_out + deep_out, label, name='model')

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