# \[Solved\] Multiple PackedSequence input ordering

**URL:** <https://discuss.pytorch.org/t/solved-multiple-packedsequence-input-ordering/2106>\
**Category:** Uncategorized\
**Created:** [April 21, 2017, 3:33pm UTC](https://discuss.pytorch.org/t/solved-multiple-packedsequence-input-ordering/2106 "2017-04-21T15:33:03Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![aron-bordin](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/aron-bordin/32/505_2.png) [@aron-bordin](https://discuss.pytorch.org/u/aron-bordin)\
**Post date:** [April 24, 2017, 11:03pm UTC](https://discuss.pytorch.org/t/solved-multiple-packedsequence-input-ordering/2106/3 "2017-04-24T23:03:01Z")

</div>

My forward function looks like:

```
   def forward(self, dict_index, features, prev_hidden, seq_sizes, original_index):
        i2e = self.embedding(dict_index)
        data = torch.cat((i2e, features), 2)

        packed = pack_padded_sequence(data, list(seq_sizes.data), batch_first=True)
        output, _ = self.rnn(packed, prev_hidden)

        output, _ = pad_packed_sequence(output, batch_first=True)
        # get the last time step for each sequence
        idx = (seq_sizes - 1).view(-1, 1).expand(output.size(0), output.size(2)).unsqueeze(1)
        decoded = output.gather(1, idx).squeeze()

        # restore the sorting
        decoded[original_index] = decoded

        return decoded

```

and then I compare the decoding using the cosine embedding. Will pytorch use the correct gradients on backward ? Do I need to modify something ? Because I’m changing the order of the data in the last step of the forward, so do I need to “reorder” the loss values ?

---

_[View the full topic](https://discuss.pytorch.org/t/solved-multiple-packedsequence-input-ordering/2106)._