LPPool2d#

classtorch.nn.modules.pooling.LPPool2d(norm_type,kernel_size,stride=None,ceil_mode=False)[source]#

Applies a 2D power-average pooling over an input signal composed of several input planes.

On each window, the function computed is:

$$f(X)=\sqrt[p]{\sum _{x\in X}{x}^p}$$f(X)=p​x∈X∑​xp​

• At p =$\mathrm{\infty }$∞, one gets Max Pooling

• At p = 1, one gets Sum Pooling (which is proportional to average pooling)

The parameterskernel_size,stride can either be:

• a singleint – in which case the same value is used for the height and width dimension

• atuple of two ints – in which case, the firstint is used for the height dimension,and the secondint for the width dimension

Note

If the sum to the power ofp is zero, the gradient of this function isnot defined. This implementation will set the gradient to zero in this case.

Parameters

• kernel_size (Union[int,tuple[int,int]]) – the size of the window

• stride (Union[int,tuple[int,int]]) – the stride of the window. Default value iskernel_size

• ceil_mode (bool) – when True, will useceil instead offloor to compute the output shape

Shape:

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

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

  $$H_{out}=\lfloor \frac{H_{in}-\text{kernel\_size}[0]}{\text{stride}[0]}+1\rfloor$$Hout​=⌊stride[0]Hin​−kernel_size[0]​+1⌋
  $$W_{out}=\lfloor \frac{W_{in}-\text{kernel\_size}[1]}{\text{stride}[1]}+1\rfloor$$Wout​=⌊stride[1]Win​−kernel_size[1]​+1⌋

Examples:

>>># power-2 pool of square window of size=3, stride=2>>>m=nn.LPPool2d(2,3,stride=2)>>># pool of non-square window of power 1.2>>>m=nn.LPPool2d(1.2,(3,2),stride=(2,1))>>>input=torch.randn(20,16,50,32)>>>output=m(input)

forward(input)[source]#

Runs the forward pass.

Return type

Tensor