ReflectionPad1d#

classtorch.nn.ReflectionPad1d(padding)[source]#

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

ForN-dimensional padding, usetorch.nn.functional.pad().

Parameters

padding (int,tuple) – the size of the padding. If isint, uses the samepadding in all boundaries. If a 2-tuple, uses($\text{padding\_left}$padding_left,$\text{padding\_right}$padding_right)Note that padding size should be less than the corresponding input dimension.

Shape:

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

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

  $W_{out}=W_{in}+\text{padding\_left}+\text{padding\_right}$Wout​=Win​+padding_left+padding_right

Examples:

>>>m=nn.ReflectionPad1d(2)>>>input=torch.arange(8,dtype=torch.float).reshape(1,2,4)>>>inputtensor([[[0., 1., 2., 3.],         [4., 5., 6., 7.]]])>>>m(input)tensor([[[2., 1., 0., 1., 2., 3., 2., 1.],         [6., 5., 4., 5., 6., 7., 6., 5.]]])>>># using different paddings for different sides>>>m=nn.ReflectionPad1d((3,1))>>>m(input)tensor([[[3., 2., 1., 0., 1., 2., 3., 2.],         [7., 6., 5., 4., 5., 6., 7., 6.]]])