You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@singa.apache.org by "wangwei (JIRA)" <ji...@apache.org> on 2015/09/26 17:13:05 UTC

[jira] [Resolved] (SINGA-51) Use Caffe's im2col and pooling implementation to accelerate conv and pooling operations

     [ https://issues.apache.org/jira/browse/SINGA-51?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

wangwei resolved SINGA-51.
--------------------------
    Resolution: Fixed
      Assignee: wangwei

> Use Caffe's im2col and pooling implementation to accelerate conv and pooling operations
> ---------------------------------------------------------------------------------------
>
>                 Key: SINGA-51
>                 URL: https://issues.apache.org/jira/browse/SINGA-51
>             Project: Singa
>          Issue Type: Improvement
>            Reporter: wangwei
>            Assignee: wangwei
>
> Currently SINGA uses [Mshadow|https://github.com/dmlc/mshadow/tree/master/doc]'s unpatch2col and pool expression in the implementation of convolution and pooling layer. After comparing them with Caffe's implementation using im2col and pooling implementation, we found the later implementation is faster. Hence we can add them into SINGA as two new layers, CaffeConvLayer and CaffePoolingLayer.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)