You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by zh...@apache.org on 2018/05/03 04:50:05 UTC
[incubator-mxnet] branch master updated: Fix learning rate of ctc
example (#10790)
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 20bbef5 Fix learning rate of ctc example (#10790)
20bbef5 is described below
commit 20bbef509f322903bf64758a3f12a81cb56134a3
Author: chinakook <ch...@msn.com>
AuthorDate: Thu May 3 12:49:58 2018 +0800
Fix learning rate of ctc example (#10790)
The training of ctc will not converge in 100 epochs with learning rate 0.001, So change it to 0.01.
---
example/ctc/hyperparams.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/example/ctc/hyperparams.py b/example/ctc/hyperparams.py
index 7289d19..cdcb874 100644
--- a/example/ctc/hyperparams.py
+++ b/example/ctc/hyperparams.py
@@ -29,7 +29,7 @@ class Hyperparams(object):
self._eval_epoch_size = 3000
self._batch_size = 128
self._num_epoch = 100
- self._learning_rate = 0.001
+ self._learning_rate = 0.01
self._momentum = 0.9
self._num_label = 4
# Network hyper parameters
--
To stop receiving notification emails like this one, please contact
zhasheng@apache.org.