You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2018/08/09 17:18:51 UTC

[GitHub] szha commented on a change in pull request #12101: Add gamma initialization and se module for gluon resnet model

szha commented on a change in pull request #12101: Add gamma initialization and se module for gluon resnet model
URL: https://github.com/apache/incubator-mxnet/pull/12101#discussion_r209011295
 
 

 ##########
 File path: python/mxnet/gluon/model_zoo/vision/resnet.py
 ##########
 @@ -56,15 +60,31 @@ class BasicBlockV1(HybridBlock):
         Whether to downsample the input.
     in_channels : int, default 0
         Number of input channels. Default is 0, to infer from the graph.
+    use_se : bool, default False
+        Whether to use Squeeze-and-Excitation module
     """
-    def __init__(self, channels, stride, downsample=False, in_channels=0, **kwargs):
+    def __init__(self, channels, stride, downsample=False, in_channels=0,
+                 last_gamma=False, use_se=False, **kwargs):
 
 Review comment:
   need to add doc for last_gamma

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services