torch.nn.functional.avg_pool3d#

torch.nn.functional.avg_pool3d(input,kernel_size,stride=None,padding=0,ceil_mode=False,count_include_pad=True,divisor_override=None)→Tensor#

Applies 3D average-pooling operation in$kT\times kH\times kW$kT×kH×kW regions by stepsize$sT\times sH\times sW$sT×sH×sW steps. The number of output features is equal to$\lfloor \frac{\text{input planes}}{sT}\rfloor$⌊sTinput planes​⌋.

SeeAvgPool3d for details and output shape.

Parameters

• input – input tensor$(\text{minibatch},\text{in\_channels},iT\times iH,iW)$(minibatch,in_channels,iT×iH,iW)

• kernel_size – size of the pooling region. Can be a single number or atuple(kT, kH, kW)

• stride – stride of the pooling operation. Can be a single number or atuple(sT, sH, sW). Default:kernel_size

• padding – implicit zero paddings on both sides of the input. Can be asingle number or a tuple(padT, padH, padW). Should be at most halfof effective kernel size, that is$((kernelSize-1)\ast dilation+1)\mathrm{/}2$((kernelSize−1)∗dilation+1)/2.Default: 0

• ceil_mode – when True, will useceil instead offloor in the formulato compute the output shape

• count_include_pad – when True, will include the zero-padding in theaveraging calculation

• divisor_override – if specified, it will be used as divisor, otherwisesize of the pooling region will be used. Default: None