AvgPool2d#

classtorch.nn.modules.pooling.AvgPool2d(kernel_size,stride=None,padding=0,ceil_mode=False,count_include_pad=True,divisor_override=None)[source]#

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

In the simplest case, the output value of the layer with input size$(N,C,H,W)$(N,C,H,W),output$(N,C,H_{out},W_{out})$(N,C,Hout​,Wout​) andkernel_size$(kH,kW)$(kH,kW)can be precisely described as:

$$out(N_i,C_j,h,w)=\frac{1}{kH\ast kW}\sum _{m=0}^{kH-1}\sum _{n=0}^{kW-1}input(N_i,C_j,stride[0]\times h+m,stride[1]\times w+n)$$out(Ni​,Cj​,h,w)=kH∗kW1​m=0∑kH−1​n=0∑kW−1​input(Ni​,Cj​,stride[0]×h+m,stride[1]×w+n)

Ifpadding is non-zero, then the input is implicitly zero-padded on both sidesforpadding number of points.

Note

When ceil_mode=True, sliding windows are allowed to go off-bounds if they start within the left paddingor the input. Sliding windows that would start in the right padded region are ignored.

Note

pad should be at most half of effective kernel size.

The parameterskernel_size,stride,padding can either be:

• a singleint or a single-element tuple – 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

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

• padding (Union[int,tuple[int,int]]) – implicit zero padding to be added on both sides

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

• count_include_pad (bool) – when True, will include the zero-padding in the averaging calculation

• divisor_override (Optional[int]) – if specified, it will be used as divisor, otherwise size of the pooling region will be used.

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

  $$H_{out}=\lfloor \frac{H_{in}+2\times \text{padding}[0]-\text{kernel\_size}[0]}{\text{stride}[0]}+1\rfloor$$Hout​=⌊stride[0]Hin​+2×padding[0]−kernel_size[0]​+1⌋
  $$W_{out}=\lfloor \frac{W_{in}+2\times \text{padding}[1]-\text{kernel\_size}[1]}{\text{stride}[1]}+1\rfloor$$Wout​=⌊stride[1]Win​+2×padding[1]−kernel_size[1]​+1⌋

  Per the note above, ifceil_mode is True and$(H_{out}-1)\times \text{stride}[0]\ge H_{in}+\text{padding}[0]$(Hout​−1)×stride[0]≥Hin​+padding[0], we skip the last window as it would start in the bottom padded region,resulting in$H_{out}$Hout​ being reduced by one.

  The same applies for$W_{out}$Wout​.

Examples:

>>># pool of square window of size=3, stride=2>>>m=nn.AvgPool2d(3,stride=2)>>># pool of non-square window>>>m=nn.AvgPool2d((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