You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@systemml.apache.org by "Mike Dusenberry (JIRA)" <ji...@apache.org> on 2017/04/12 21:37:41 UTC
[jira] [Commented] (SYSTEMML-1516) Improve output size calculation
in conv2d & max_pool2d
[ https://issues.apache.org/jira/browse/SYSTEMML-1516?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15966684#comment-15966684 ]
Mike Dusenberry commented on SYSTEMML-1516:
-------------------------------------------
[PR 459 | https://github.com/apache/incubator-systemml/pull/459] submitted.
> Improve output size calculation in conv2d & max_pool2d
> ------------------------------------------------------
>
> Key: SYSTEMML-1516
> URL: https://issues.apache.org/jira/browse/SYSTEMML-1516
> Project: SystemML
> Issue Type: Sub-task
> Reporter: Mike Dusenberry
> Assignee: Mike Dusenberry
> Priority: Minor
>
> The calculation of the output sizes (`Hout`, `Wout`) for conv2d and
> max_pool2d layers rely on a flooring operation to only allow for valid
> operations. Currently, we simply rely on the `as.integer` call to
> implicitly perform this flooring operation during truncation of the double
> to an integer. While this gives the correct results, it is less
> readable than it should be, and relies on truncation behavior than explicit mathematical behavior. We should simply add an explicit `floor`
> operation to each calculation.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)