I have a sequences collection in the following form:

```
sequences = torch.tensor([[2,1],[5,6],[3,0])
indexes = torch.tensor([1,0,1])
```

that is, the sequence `0`

is made of just `[5,6]`

, and the sequence `1`

is made of `[2,1] , [3,0]`

. Mathematically `sequence[i] = { sequences[j] such that i = indexes[j] }`

I need to feed these sequences into an LSTM. Since these are variable-length sequences, pytorch documentation states to use something like `torch.nn.utils.rnn.pack_sequence`

.

Sadly, this method and its like want, as input, a list of tensors where each of them is a `L x *`

, with L being the length of the single sequence.

How can build something that can be fed into a pytorch LSTM?

P.s. throughout the code I work with these tensors using `scatter`

and `gather`

functionalities but I canâ€™t find a way to use them to achieve this goal.

p.p.s I posted this question also on stackoverflow