mindspore.ops.reverse_sequence

mindspore.ops.reverse_sequence(x, seq_lengths, seq_dim, batch_dim=0)[source]

Reverses variable length slices.

Parameters

  • x (Tensor) – The input to reverse, supporting all number types including bool.

  • seq_lengths (Tensor) – Specified reversing length, must be a 1-D vector with int32 or int64 types.

  • seq_dim (int) – The dimension where reversal is performed. Required.

  • batch_dim (int) – The input is sliced in this dimension. Default: 0 .

Returns

Tensor, with the same shape and data type as x.

Raises

  • TypeError – If seq_dim or batch_dim is not an int.

  • ValueError – If \(len(seq\_lengths) != x.shape[batch\_dim]\).

  • ValueError – If \(batch\_dim == seq\_dim\).

  • ValueError – If \(seq\_dim < 0\) or \(seq\_dim >= len(x.shape)\).

  • ValueError – If \(batch\_dim < 0\) or \(batch\_dim >= len(x.shape)\).

  • RuntimeError – If any value of seq_lengths is less than 0.

  • RuntimeError – If any value of seq_lengths is larger than x.shape[seq_dim].

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> x = Tensor(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), mindspore.float32)
>>> seq_lengths = Tensor(np.array([1, 2, 3]))
>>> output = ops.reverse_sequence(x, seq_lengths, seq_dim=1)
>>> print(output)
[[1. 2. 3.]
 [5. 4. 6.]
 [9. 8. 7.]]
>>> x = Tensor(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), mindspore.float32)
>>> seq_lengths = Tensor(np.array([1, 2, 3]))
>>> output = ops.reverse_sequence(x, seq_lengths, seq_dim=0, batch_dim=1)
>>> print(output)
[[1. 5. 9.]
 [4. 2. 6.]
 [7. 8. 3.]]
>>> x = Tensor(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), mindspore.float32)
>>> seq_lengths = Tensor(np.array([2, 2, 3]))
>>> output = ops.reverse_sequence(x, seq_lengths, seq_dim=1)
>>> print(output)
[[2. 1. 3.]
 [5. 4. 6.]
 [9. 8. 7.]]
>>> x = Tensor(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), mindspore.float32)
>>> seq_lengths = Tensor(np.array([3, 2, 3]))
>>> output = ops.reverse_sequence(x, seq_lengths, seq_dim=1)
>>> print(output)
[[3. 2. 1.]
 [5. 4. 6.]
 [9. 8. 7.]]
>>> x = Tensor(np.array([[1, 2, 3, 4], [5, 6, 7, 8]]), mindspore.float32)
>>> seq_lengths = Tensor(np.array([4, 4]))
>>> output = ops.reverse_sequence(x, seq_lengths, seq_dim=1)
>>> print(output)
[[4. 3. 2. 1.]
 [8. 7. 6. 5.]]