AvgPool3d#

classtorch.nn.modules.pooling.AvgPool3d(kernel_size,stride=None,padding=0,ceil_mode=False,count_include_pad=True,divisor_override=None)[source]#

Applies a 3D average pooling over an input signal composed of several input planes.

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

out(Ni​,Cj​,d,h,w)=​k=0∑kD−1​m=0∑kH−1​n=0∑kW−1​kD×kH×kWinput(Ni​,Cj​,stride[0]×d+k,stride[1]×h+m,stride[2]×w+n)​​

Ifpadding is non-zero, then the input is implicitly zero-padded on all three 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 can either be:

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

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

Parameters

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

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

• padding (Union[int,tuple[int,int,int]]) – implicit zero padding to be added on all three 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, otherwisekernel_size will be used

Shape:

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

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

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

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

  The same applies for$W_{out}$Wout​ and$H_{out}$Hout​.

Examples:

>>># pool of square window of size=3, stride=2>>>m=nn.AvgPool3d(3,stride=2)>>># pool of non-square window>>>m=nn.AvgPool3d((3,2,2),stride=(2,1,2))>>>input=torch.randn(20,16,50,44,31)>>>output=m(input)

forward(input)[source]#

Runs the forward pass.

Return type

Tensor