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 2018/04/30 23:04:08 UTC

[GitHub] anirudhacharya opened a new issue #10754: Support for LpPooling in Pooling operator

anirudhacharya opened a new issue #10754: Support for LpPooling in Pooling operator
URL: https://github.com/apache/incubator-mxnet/issues/10754
 
 
   [Pooling operator](http://mxnet.incubator.apache.org/api/python/ndarray/ndarray.html#mxnet.ndarray.Pooling) currently supports ‘avg’, ‘max’ and ‘sum’ pooling. There is no support for lp pooling. 
   
   LpPooling is computed by calculating the Lp norm on all values of a subset of the input tensor according to the kernel size and then down-sampling the data into the output tensor.  Pytorch and Caffe2 have support for this operator.
   
   The existing Pooling operator should be modified to support Lp pooling.
   
   @piiswrong @szha @zheng-da @haojin2 @eric-haibin-lin 

----------------------------------------------------------------
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