# Passing a minibatchs of sequential data through a bidirectional rnn

**URL:** <https://discuss.pytorch.org/t/passing-a-minibatchs-of-sequential-data-through-a-bidirectional-rnn/46022>\
**Category:** Uncategorized\
**Created:** [May 23, 2019, 12:17pm UTC](https://discuss.pytorch.org/t/passing-a-minibatchs-of-sequential-data-through-a-bidirectional-rnn/46022 "2019-05-23T12:17:45Z")\
**Posts on this page:** 1\
**Showing post:** 4

<div class="post-metadata">

**Author:** ![vdw](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/vdw/32/10074_2.png) [@vdw](https://discuss.pytorch.org/u/vdw)\
**Post date:** [May 31, 2019, 10:01am UTC](https://discuss.pytorch.org/t/passing-a-minibatchs-of-sequential-data-through-a-bidirectional-rnn/46022/4 "2019-05-31T10:01:44Z")

</div>

If the splitting makes sense depends on your data and task.

You can have a look at [this thread](https://discuss.pytorch.org/t/tensorflow-esque-bucket-by-sequence-length/41284/13) to generate batches of sequences of equal length. I use this all the time since it’s worry-free: neither padding nor packing is needed.

---

_[View the full topic](https://discuss.pytorch.org/t/passing-a-minibatchs-of-sequential-data-through-a-bidirectional-rnn/46022)._