mindspore.mint.nn.ConstantPad1d

class mindspore.mint.nn.ConstantPad1d(padding, value)[source]

Apply a 1-D constant padding to the last dimension of the input tensor using padding and value.

For more information, please refer to mindspore.mint.nn.functional.pad().

Warning

This is an experimental API that is subject to change or deletion.

Parameters:

padding (Union[int, tuple[int], list[int]]) –
Specifies the padding size.
- If an int, the same padding is applied to all boundaries.
- If a tuple or list, the order is \((\text{padding_left}, \text{padding_right})\).
value (Union[int, float]) – Specifies the padding value.

Inputs:

input (Tensor) - The input tensor with shape \((N, *)\), where \(*\) means any number of additional dimensions.

Outputs:

Tensor, the padded tensor.

Raises:

ValueError – If the output dimension computed by padding is negative.
ValueError – If padding is a tuple or list, and the length does not match the tensor dimension.

Supported Platforms:: Ascend

Examples

>>> import mindspore
>>> x = mindspore.mint.ones((1, 2, 3, 4), dtype=mindspore.float32)
>>> x = mindspore.tensor(x)
>>> # padding is tuple
>>> padding = (0, 1)
>>> value = 0.5
>>> pad1d = mindspore.mint.nn.ConstantPad1d(padding, value)
>>> out = pad1d(x)
>>> print(out)
[[[[1.  1.  1.  1.  0.5]
   [1.  1.  1.  1.  0.5]
   [1.  1.  1.  1.  0.5]]
  [[1.  1.  1.  1.  0.5]
   [1.  1.  1.  1.  0.5]
   [1.  1.  1.  1.  0.5]]]]
>>> print(out.shape)
(1, 2, 3, 5)
>>> # padding is int
>>> padding = 1
>>> value = 0.5
>>> pad1d = mindspore.mint.nn.ConstantPad1d(padding, value)
>>> out = pad1d(x)
>>> print(out)
[[[[0.5 1.  1.  1.  1.  0.5]
   [0.5 1.  1.  1.  1.  0.5]
   [0.5 1.  1.  1.  1.  0.5]]
  [[0.5 1.  1.  1.  1.  0.5]
   [0.5 1.  1.  1.  1.  0.5]
   [0.5 1.  1.  1.  1.  0.5]]]]
>>> print(out.shape)
(1, 2, 3, 6)