systemml-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Glenn Weidner (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (SYSTEMML-1686) Transpose Conv2d has incorrect filter shape and incorrect input size argument
Date Sat, 09 Sep 2017 01:42:00 GMT

     [ https://issues.apache.org/jira/browse/SYSTEMML-1686?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Glenn Weidner updated SYSTEMML-1686:
------------------------------------
    Fix Version/s:     (was: SystemML 1.0)
                   SystemML 0.15

> Transpose Conv2d has incorrect filter shape and incorrect input size argument
> -----------------------------------------------------------------------------
>
>                 Key: SYSTEMML-1686
>                 URL: https://issues.apache.org/jira/browse/SYSTEMML-1686
>             Project: SystemML
>          Issue Type: Bug
>    Affects Versions: SystemML 1.0
>            Reporter: Mike Dusenberry
>            Assignee: Matthias Boehm
>             Fix For: SystemML 0.15
>
>
> Currently, the transpose conv2d layer ([{{nn/layers/conv2d_tranpose.dml}} | https://github.com/apache/systemml/blob/master/scripts/nn/layers/conv2d_transpose.dml]
has a bug in which the filters tensor {{W}} has an incorrect shape, and the {{conv2d_backward_data}}
op has an incorrect input shape argument.  This results in an exception when the number of
input channels {{C}} is not equal to the number of filters {{F}} (i.e. number of output channels).
 Since the transpose conv2d op is the gradient of the conv2d op, the filter tensor needs to
have the shape {{C, F, Hf, Wf}} for {{F}} filters, rather than {{F, C, Hf, Wf}}, in order
to map from an input with {{C}} channels to an output with {{F}} channels during the input
data gradient function  ({{conv2d_backward_data}}) that is used in the forward pass.  Additionally,
the {{input_shape}} argument for {{conv2d_backward_data}} needs to be {{N, F, Hout, Wout}},
rather than {{N, C, Hout, Wout}} in order to map from an input with {{C}} channels to an output
with {{F}} channels.  Our current test cases did not catch this issue because the tests used
{{C = F = 1}}.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

Mime
View raw message