[
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: [email protected]
For additional commands, e-mail: [email protected]
