# RNN Utils¶

class nnabla.utils.rnn.PackedSequence[source]
Parameters

Pad a list of variable-length Variables.

This method stacks a list of variable-length nnabla.Variable s with the padding_value.

$$T_i$$ is the length of the $$i$$-th Variable in the sequences. $$B$$ is the batch size equal to the length of the sequences. $$T$$ is the max of $$T_i$$ for all $$i$$. $$*$$ is the remaining dimensions including none.

Note

This function must be used the dynamic computation mode.

Example:

import numpy as np
import nnabla as nn
import nnabla.functions as F
import nnabla.utils.rnn as rnn_utils

nn.set_auto_forward(True)

l2v = lambda ldata: nn.Variable.from_numpy_array(np.asarray(ldata))
a = l2v([1, 1, 1, 1])
b = l2v([2, 2, 2])
c = l2v([2, 2, 2])
d = l2v([3, 3])
e = l2v([3, 3])
sequences = [a, b, c, d, e]


Parameters
• sequences (list of nnabla.Variable) – Sequence of the variable of ($$T_i$$, $$*$$) shape.

• batch_first (bool) – If False, output is of ($$T$$, $$B$$, $$*$$) shape, otherwise ($$B$$, $$T$$, $$*$$).

Returns

nnabla.Variable of ($$T$$, $$B$$, $$*$$) or ($$B$$, $$T$$, $$*$$) shape

This method packs a padded variable-length sequences.

$$T$$ is the max length over the lengths of sequences. $$B$$ is the batch size equal to the length of the sequences. $$*$$ is the remaining dimensions including none.

Note

This function must be used the dynamic computation mode.

Example:

import numpy as np
import nnabla as nn
import nnabla.functions as F
import nnabla.utils.rnn as rnn_utils

nn.set_auto_forward(True)

l2v = lambda ldata: nn.Variable.from_numpy_array(np.asarray(ldata))
a = l2v([1, 1, 1, 1])
b = l2v([2, 2, 2])
c = l2v([2, 2, 2])
d = l2v([3, 3])
e = l2v([3, 3])
sequences = [a, b, c, d, e]
lengths = l2v([seq.shape for seq in sequences])

print(packed_sequence.data.d)
print(packed_sequence.batch_sizes.d)

Parameters
• padded_sequence (nnabla.Variable) – Padded sequence of ($$T \times B \times *$$) or ($$B \times T \times *$$) shape.

• lengths (nnabla.Variable) – Sequence length for each batch and always resides in CPU.

• batch_first (bool) – padded_sequence is of ($$T$$, $$B$$, $$*$$) shape if False, otherwise ($$B$$, $$T$$, $$*$$).

• enforce_sorted (bool) – Sequences are sorted by the length in a decreasing order if True. Default is True.

Returns

PackedSequence

nnabla.utils.rnn.pack_sequence(sequences, batch_first=False, enforce_sorted=True)[source]

Pack a list of variable-length Variables.

This method packs a list of variable-length Variables.

$$T_i$$ is the length of the $$i$$-th Variable in the sequences. $$T$$ is the max of $$T_i$$ for all $$i$$. $$B$$ is the batch size equal to the length of the sequences. $$*$$ is the remaining dimensions including none.

Note

This function must be used the dynamic computation mode.

Example:

import numpy as np
import nnabla as nn
import nnabla.functions as F
import nnabla.utils.rnn as rnn_utils

nn.set_auto_forward(True)

l2v = lambda ldata: nn.Variable.from_numpy_array(np.asarray(ldata))
a = l2v([3, 3])
b = l2v([2, 2, 2])
c = l2v([2, 2, 2])
d = l2v([1, 1, 1, 1])
e = l2v([3, 3])
sequences = [a, b, c, d, e]

packed_sequence = rnn_utils.pack_sequence(sequences, enforce_sorted=False)
print(packed_sequence.data.d)
print(packed_sequence.batch_sizes.d)

Parameters
Returns

packed_sequence

Return type

PackedSequence

This method unpacks the packed sequqnce and pad it, the inverse operation of pack_padded_sequence().

$$T_i$$ is the length of the $$i$$-th Variable in the sequences. $$B$$ is the batch size equal to the length of the sequences. $$T$$ is the max of $$T_i$$ for all $$i$$. $$*$$ is the remaining dimensions including none.

Note

This function must be used the dynamic computation mode.

Example:

import numpy as np
import nnabla as nn
import nnabla.functions as F
import nnabla.utils.rnn as rnn_utils

nn.set_auto_forward(True)

l2v = lambda ldata: nn.Variable.from_numpy_array(np.asarray(ldata))
a = l2v([3, 3])
b = l2v([2, 2, 2])
c = l2v([2, 2, 2])
d = l2v([1, 1, 1, 1])
e = l2v([3, 3])
sequences = [a, b, c, d, e]

packed_sequence = rnn_utils.pack_sequence(sequences, enforce_sorted=False)
print(packed_sequence.data.d)
print(packed_sequence.batch_sizes.d)

print(lengths.d)

Parameters
• sequence (PackedSequence) – PackedSequence.

• batch_first (bool) – If False, output is of ($$T$$, $$B$$, $$*$$) shape, otherwise ($$B$$, $$T$$, $$*$$).

• total_length (int) – If not None, the outputs are padded up to the total_length. If the total_length is less than the max length in the sequences, the error is thrown. This is normally used in the distributed training to align with the longest sequence in a distributed system.
nnabla.Variable of ($$T$$, $$B$$, $$*$$) or ($$B$$, $$T$$, $$*$$) shape