ReflectionPad2d — PyTorch 2.7 documentation (original) (raw)

class torch.nn.ReflectionPad2d(padding)[source][source]¶

Pads the input tensor using the reflection of the input boundary.

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 (padding_left\text{padding\_left},padding_right\text{padding\_right}, padding_top\text{padding\_top}, padding_bottom\text{padding\_bottom}) Note that padding size should be less than the corresponding input dimension.

Shape:

• Input: (N,C,Hin,Win)(N, C, H_{in}, W_{in}) or (C,Hin,Win)(C, H_{in}, W_{in}).
• Output: (N,C,Hout,Wout)(N, C, H_{out}, W_{out}) or (C,Hout,Wout)(C, H_{out}, W_{out}) where
  Hout=Hin+padding_top+padding_bottomH_{out} = H_{in} + \text{padding\_top} + \text{padding\_bottom}
  Wout=Win+padding_left+padding_rightW_{out} = W_{in} + \text{padding\_left} + \text{padding\_right}

Examples:

m = nn.ReflectionPad2d(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([[[[8., 7., 6., 7., 8., 7., 6.], [5., 4., 3., 4., 5., 4., 3.], [2., 1., 0., 1., 2., 1., 0.], [5., 4., 3., 4., 5., 4., 3.], [8., 7., 6., 7., 8., 7., 6.], [5., 4., 3., 4., 5., 4., 3.], [2., 1., 0., 1., 2., 1., 0.]]]])

using different paddings for different sides

m = nn.ReflectionPad2d((1, 1, 2, 0)) m(input) tensor([[[[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.]]]])