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

Posted to issues@systemml.apache.org by "Niketan Pansare (JIRA)" <ji...@apache.org> on 2017/03/10 00:47:38 UTC

[jira] [Created] (SYSTEMML-1384) Revisit the weight and bias of fully connected layer

Niketan Pansare created SYSTEMML-1384:
-----------------------------------------

             Summary: Revisit the weight and bias of fully connected layer
                 Key: SYSTEMML-1384
                 URL: https://issues.apache.org/jira/browse/SYSTEMML-1384
             Project: SystemML
          Issue Type: Sub-task
            Reporter: Niketan Pansare


Since all our bias are column vector (which is consistent with Keras/Caffe), whereas bias of fully connected layer is a row-vector. Similarly, the weight that is passed to caffe is transpose of weights passed to SystemML (since both store in row-major NCHW format).

Making the dimensions consistent will simplify loading of Caffe/Keras models.

[~mwdusenb@us.ibm.com]



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)