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 2015/12/27 15:34:49 UTC

[jira] [Created] (SINGA-116) Fix a bug in InnerProductLayer caused by weight matrix sharing

wangwei created SINGA-116:
-----------------------------

             Summary: 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)