avg_pool2d#

classtorch.ao.nn.quantized.functional.avg_pool2d(input,kernel_size,stride=None,padding=0,ceil_mode=False,count_include_pad=True,divisor_override=None)[source]#

Applies 2D average-pooling operation in$kH\times kW$kH×kW regions by step size$sH\times sW$sH×sW steps. The number of output features is equal to the number ofinput planes.

Note

The input quantization parameters propagate to the output.

SeeAvgPool2d for details and output shape.

Parameters

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

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

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

• padding – implicit zero paddings on both sides of the input. Can be asingle number or a tuple(padH, padW). Default: 0

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

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

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