[ https://issues.apache.org/jira/browse/SYSTEMML-1674?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16054725#comment-16054725 ]
Mike Dusenberry commented on SYSTEMML-1674: ------------------------------------------- cc [~niketanpansare], [~reinwald], [~reinw...@us.ibm.com] > Add a new 2D depthwise convolution layer > ---------------------------------------- > > Key: SYSTEMML-1674 > URL: https://issues.apache.org/jira/browse/SYSTEMML-1674 > Project: SystemML > Issue Type: Sub-task > Reporter: Mike Dusenberry > Assignee: Mike Dusenberry > Fix For: SystemML 1.0 > > > A depthwise convolution (1) applies a different set of M filters to each > input channel separately, thus expanding each input channel to M output > channels, and (2) concatenates the results into a single volume with C*M > output channels. This is in contrast to a regular 2D 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)