CircularPad2d

class torch.nn.CircularPad2d(padding)

Pads the input tensor using circular padding of the input boundary.

Tensor values at the beginning of the dimension are used to pad the end, and values at the end are used to pad the beginning. If negative padding is applied then the ends of the tensor get removed.

For N-dimensional padding, use torch.nn.functional.pad().

Parameters

padding (int, tuple) – the size of the padding. If is int, uses the same padding in all boundaries. If a 4-tuple, uses ($\text{padding\_left}$, $\text{padding\_right}$, $\text{padding\_top}$, $\text{padding\_bottom}$)

Shape:

• Input: $(N, C, H_{in}, W_{in})$ or $(C, H_{in}, W_{in})$.

• Output: $(N, C, H_{out}, W_{out})$ or $(C, H_{out}, W_{out})$, where

  $H_{out} = H_{in} + \text{padding\_top} + \text{padding\_bottom}$

  $W_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}$

Examples:

>>> m = nn.CircularPad2d(2)
>>> input = torch.arange(9, dtype=torch.float).reshape(1, 1, 3, 3)
>>> input
tensor([[[[0., 1., 2.],
          [3., 4., 5.],
          [6., 7., 8.]]]])
>>> m(input)
tensor([[[[4., 5., 3., 4., 5., 3., 4.],
          [7., 8., 6., 7., 8., 6., 7.],
          [1., 2., 0., 1., 2., 0., 1.],
          [4., 5., 3., 4., 5., 3., 4.],
          [7., 8., 6., 7., 8., 6., 7.],
          [1., 2., 0., 1., 2., 0., 1.],
          [4., 5., 3., 4., 5., 3., 4.]]]])
>>> # using different paddings for different sides
>>> m = nn.CircularPad2d((1, 1, 2, 0))
>>> m(input)
tensor([[[[5., 3., 4., 5., 3.],
          [8., 6., 7., 8., 6.],
          [2., 0., 1., 2., 0.],
          [5., 3., 4., 5., 3.],
          [8., 6., 7., 8., 6.]]]])