Xingjian Shi created MXNET-31:

             Summary: Support variable sequence length in gluon.RecurrentCell
                 Key: MXNET-31
             Project: Apache MXNet
          Issue Type: New Feature
            Reporter: Xingjian Shi
            Assignee: Chris Olivier

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

To unsubscribe, e-mail:
For additional commands, e-mail:

Reply via email to