[
https://issues.apache.org/jira/browse/SINGA-116?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15072428#comment-15072428
]
ASF subversion and git services commented on SINGA-116:
-------------------------------------------------------
Commit cf6ef8247420b0869b1f93613ad47420f73ee2d4 in incubator-singa's branch
refs/heads/master from [~flytosky]
[ https://git-wip-us.apache.org/repos/asf?p=incubator-singa.git;h=cf6ef82 ]
SINGA-116 Fix a bug in InnerProductLayer caused by weight matrix sharing
Fix the bug by considering the tranpose of weight matrix explicitly.
> Fix a bug in InnerProductLayer caused by weight matrix sharing
> --------------------------------------------------------------
>
> Key: SINGA-116
> URL: https://issues.apache.org/jira/browse/SINGA-116
> Project: Singa
> Issue Type: Bug
> Reporter: wangwei
> Assignee: wangwei
>
> There is a bug in the implementation of InnerProductLayer, which appears when
> training the auto-encoder example.
> The weight matrix in inner-product layer in the encoder is shared by another
> layer in the decoder. But the decoder uses transposed version.
> The current code does not handle matrix transposition.
> The bug can be fixed considering the transpose_ field explicitly.
> We may later handle it implicitly using a Tensor class that handles
> transposition automatically.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
