Details
-
New Feature
-
Status: Done
-
Major
-
Resolution: Fixed
-
None
-
None
Description
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.
Attachments
Issue Links
- links to
