You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@systemml.apache.org by "Glenn Weidner (JIRA)" <ji...@apache.org> on 2017/09/09 05:08:00 UTC
[jira] [Updated] (SYSTEMML-1675) Add a new 2D depthwise transpose
convolution layer
[ https://issues.apache.org/jira/browse/SYSTEMML-1675?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Glenn Weidner updated SYSTEMML-1675:
------------------------------------
Fix Version/s: (was: SystemML 1.0)
SystemML 0.15
> Add a new 2D depthwise transpose convolution layer
> --------------------------------------------------
>
> Key: SYSTEMML-1675
> URL: https://issues.apache.org/jira/browse/SYSTEMML-1675
> Project: SystemML
> Issue Type: New Feature
> Reporter: Mike Dusenberry
> Assignee: Mike Dusenberry
> Fix For: SystemML 0.15
>
>
> A depthwise transpose convolution (1) applies a different filter to each unique group of M input channels separately, thus condensing each group of M input channels to 1 output channel, and (2) concatenates the results into a single volume with C/M output channels. This is in contrast to a regular 2D transpose convolution, in which all of the filters would be applied to all of the input channels at once.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)