# Bidirectional lstm batched padded sequence

**URL:** <https://discuss.pytorch.org/t/bidirectional-lstm-batched-padded-sequence/67462>\
**Category:** nlp\
**Created:** [January 23, 2020, 11:35am UTC](https://discuss.pytorch.org/t/bidirectional-lstm-batched-padded-sequence/67462 "2020-01-23T11:35:46Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [January 24, 2020, 5:56am UTC](https://discuss.pytorch.org/t/bidirectional-lstm-batched-padded-sequence/67462/2 "2020-01-24T05:56:50Z")

</div>

I’m not sure to completely understand your use case, but I usually refer to @vdw’s [post](https://discuss.pytorch.org/t/rnn-output-vs-hidden-state-dont-match-up-my-misunderstanding/43280) to get a quick recap how to slice which output.

---

_[View the full topic](https://discuss.pytorch.org/t/bidirectional-lstm-batched-padded-sequence/67462)._