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 2017/06/30 23:39:00 UTC
[jira] [Resolved] (SYSTEMML-1676) Add a new 2D softmax layer
[ https://issues.apache.org/jira/browse/SYSTEMML-1676?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Mike Dusenberry resolved SYSTEMML-1676.
---------------------------------------
Resolution: Fixed
Fix Version/s: SystemML 1.0
Merged in [commit 9e6715d | https://github.com/apache/systemml/commit/9e6715dafa7d47104ad8b6c6c1d39fc9423905aa].
> Add a new 2D softmax layer
> --------------------------
>
> Key: SYSTEMML-1676
> URL: https://issues.apache.org/jira/browse/SYSTEMML-1676
> Project: SystemML
> Issue Type: New Feature
> Reporter: Mike Dusenberry
> Assignee: Fei Hu
> Fix For: SystemML 1.0
>
>
> A 2D softmax layer would accept a tensor of shape {{(N,C,H,W)}}, where the {{C}} axis contains scores for {{D}} classes, and output a tensor of the same shape, with the scores transformed to normalized probabilities. The typical use case would be a segmentation problem, in which every pixel has a multiclass prediction.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)