mindspore.ops.reverse_sequence

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

Partially reverse the input sequence.

Parameters

x (Tensor) – The input tensor.
seq_lengths (Tensor) – The specified reversing length.
seq_dim (int) – The specified dimension for reversal.
batch_dim (int) – The specified slice dimension. Default 0 .

Returns

Tensor

Supported Platforms:: Ascend GPU CPU

Examples

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