[GitHub] chinakook commented on issue #7596: "is_1x1_" in convolution operator is not really used

[gi...@git.apache.org]

chinakook commented on issue #7596: "is_1x1_" in convolution operator is not really used
URL: https://github.com/apache/incubator-mxnet/issues/7596#issuecomment-324794901
 
 
   [The 3.2 section](https://arxiv.org/abs/1704.04861) of Mobilenet paper have mentioned that. I found the 1x1 convolution(with stride 1 and pad 0) is commonly used in almost all modern networks such as Googlenet/Inception/Resnet/ResNeXt too. When these networks are used in detection or segmetation, the intermediate feature maps will become very large, so the im2col skipped 1x1 convolution operation might save a lot of memory and computing resource.
   
 
----------------------------------------------------------------
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