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 2018/02/13 19:07:55 UTC
[incubator-mxnet] branch master updated: Using the "global_pool"
option to avoid an unmatching input shape of (#9783)
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 f57073e Using the "global_pool" option to avoid an unmatching input shape of (#9783)
f57073e is described below
commit f57073eb70cc1a696bd6255d292cb014da6405f1
Author: Shufan <33...@users.noreply.github.com>
AuthorDate: Wed Feb 14 03:07:49 2018 +0800
Using the "global_pool" option to avoid an unmatching input shape of (#9783)
the last average pooling layer of GoogleNet
---
example/image-classification/symbols/googlenet.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/example/image-classification/symbols/googlenet.py b/example/image-classification/symbols/googlenet.py
index 05f33da..6745ba7 100644
--- a/example/image-classification/symbols/googlenet.py
+++ b/example/image-classification/symbols/googlenet.py
@@ -65,7 +65,7 @@ def get_symbol(num_classes = 1000, **kwargs):
pool5 = mx.sym.Pooling(in4e, kernel=(3, 3), stride=(2, 2), pool_type="max")
in5a = InceptionFactory(pool5, 256, 160, 320, 32, 128, "max", 128, name="in5a")
in5b = InceptionFactory(in5a, 384, 192, 384, 48, 128, "max", 128, name="in5b")
- pool6 = mx.sym.Pooling(in5b, kernel=(7, 7), stride=(1,1), pool_type="avg")
+ pool6 = mx.sym.Pooling(in5b, kernel=(7, 7), stride=(1,1), global_pool=True, pool_type="avg")
flatten = mx.sym.Flatten(data=pool6)
fc1 = mx.sym.FullyConnected(data=flatten, num_hidden=num_classes)
softmax = mx.symbol.SoftmaxOutput(data=fc1, name='softmax')
--
To stop receiving notification emails like this one, please contact
jxie@apache.org.