mindspore.mint.nn.ReflectionPad2d

class mindspore.mint.nn.ReflectionPad2d(padding)

Pad the last 2-D dimensions of input tensor using the reflection of the input boundary.

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 it is an int, pads all boundaries with the same amount.

• If it is a tuple or list, it should be in the order \((\text{padding_left}, \text{padding_right}, \text{padding_top}, \text{padding_bottom})\).

Inputs:

• input (Tensor) - The input tensor with shape \((C, H_{in}, W_{in})\) or \((N, C, H_{in}, W_{in})\).

Outputs:

Tensor, the tensor after padding, with shape \((C, H_{out}, W_{out})\) or \((N, C, H_{out}, W_{out})\), where

• \(H_{out} = H_{in} + \text{padding_top} + \text{padding_bottom}\)

• \(W_{out} = W_{in} + \text{padding_left} + \text{padding_right}\)

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> x = mindspore.tensor([[[0, 1, 2], [3, 4, 5], [6, 7, 8]]], mindspore.float32)
>>> padding = (1, 1, 2, 0)
>>> pad2d = mindspore.mint.nn.ReflectionPad2d(padding)
>>> out = pad2d(x)
>>> print(out)
[[[7. 6. 7. 8. 7.]
  [4. 3. 4. 5. 4.]
  [1. 0. 1. 2. 1.]
  [4. 3. 4. 5. 4.]
  [7. 6. 7. 8. 7.]]]