You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@mxnet.apache.org by "Xingjian Shi (JIRA)" <ji...@apache.org> on 2018/03/09 00:35:00 UTC
[jira] [Updated] (MXNET-31) Support variable sequence length in
gluon.RecurrentCell
[ https://issues.apache.org/jira/browse/MXNET-31?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Xingjian Shi updated MXNET-31:
------------------------------
Resolution: Fixed
Status: Done (was: To Do)
> Support variable sequence length in gluon.RecurrentCell
> -------------------------------------------------------
>
> Key: MXNET-31
> URL: https://issues.apache.org/jira/browse/MXNET-31
> Project: Apache MXNet
> Issue Type: New Feature
> Reporter: Xingjian Shi
> Priority: Major
>
> When the input sequences have different lengths, the common approach is to pad them to the same length and feed the padded data into the recurrent neural network. To deal with this scenario, this PR adds a new {{valid_length}} option in {{unroll}}. {{valid_length}} refers to the real length of the sequences before padding. When the {{valid_length}} is given, the last valid state will be returned and the padded portion in the output will be masked to be zero. This feature is essential for implementing a NMT model.
--
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