torch.nn.utils.rnn.pack_sequence#

torch.nn.utils.rnn.pack_sequence(sequences,enforce_sorted=True)[source]#

Packs a list of variable length Tensors.

Consecutive call of the next functions:pad_sequence,pack_padded_sequence.

sequences should be a list of Tensors of sizeLx*, whereL isthe length of a sequence and* is any number of trailing dimensions,including0.

For unsorted sequences, useenforce_sorted = False. Ifenforce_sortedisTrue, the sequences should be sorted in the order of decreasing length.enforce_sorted=True is only necessary for ONNX export.

Example

>>>fromtorch.nn.utils.rnnimportpack_sequence>>>a=torch.tensor([1,2,3])>>>b=torch.tensor([4,5])>>>c=torch.tensor([6])>>>pack_sequence([a,b,c])PackedSequence(data=tensor([1, 4, 6, 2, 5, 3]), batch_sizes=tensor([3, 2, 1]), sorted_indices=None, unsorted_indices=None)

Parameters

• sequences (list[Tensor]) – A list of sequences of decreasing length.

• enforce_sorted (bool,optional) – ifTrue, checks that the inputcontains sequences sorted by length in a decreasing order. IfFalse, this condition is not checked. Default:True.

Returns

aPackedSequence object

Return type

PackedSequence