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

Posted to issues@mxnet.apache.org by "Anirudh Subramanian (JIRA)" <ji...@apache.org> on 2018/04/04 20:49:00 UTC

[jira] [Updated] (MXNET-218) Why does running 1 round of an MXNET model training produce Train-mse=NaN?

     [ https://issues.apache.org/jira/browse/MXNET-218?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Anirudh Subramanian updated MXNET-218:
--------------------------------------
    Description: https://github.com/apache/incubator-mxnet/issues/9358  (was: Fix in review)

> Why does running 1 round of an MXNET model training produce Train-mse=NaN?
> --------------------------------------------------------------------------
>
>                 Key: MXNET-218
>                 URL: https://issues.apache.org/jira/browse/MXNET-218
>             Project: Apache MXNet
>          Issue Type: Bug
>            Reporter: Anirudh Subramanian
>            Assignee: Rajan
>            Priority: Major
>
> https://github.com/apache/incubator-mxnet/issues/9358



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@mxnet.apache.org
For additional commands, e-mail: issues-help@mxnet.apache.org