mindspore.mint.nn.ConstantPad2d

class mindspore.mint.nn.ConstantPad2d(padding, value)[source]

Pad the last 2-D dimensions of 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, list]) –
Specifies padding size.
- If an int, the same padding is applied to all boundaries.
- If a tuple or list, the order is \((\text{padding_left}, \text{padding_right}, \text{padding_top}, \text{padding_bottom})\).
value (Union[int, float]) – Specifies padding value.

Inputs:

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

Outputs:

Tensor, the tensor after padding.

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> x = mindspore.mint.ones((1, 2, 3, 4), dtype=mindspore.float32)
>>> padding = (1, 1, 0, 1)
>>> value = 0.5
>>> pad2d = mindspore.mint.nn.ConstantPad2d(padding, value)
>>> out = pad2d(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  0.5 0.5 0.5 0.5 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  0.5 0.5 0.5 0.5 0.5]]]]
>>> print(out.shape)
(1, 2, 4, 6)