torch.nn.functional.fractional_max_pool2d#

torch.nn.functional.fractional_max_pool2d(input,kernel_size,output_size=None,output_ratio=None,return_indices=False,_random_samples=None)[source]#

Applies 2D fractional max pooling over an input signal composed of several input planes.

Fractional MaxPooling is described in detail in the paperFractional MaxPooling by Ben Graham

The max-pooling operation is applied in$kH\times kW$kH×kW regions by a stochasticstep size determined by the target output size.The number of output features is equal to the number of input planes.

Parameters

• kernel_size – the size of the window to take a max over.Can be a single number$k$k (for a square kernel of$k\times k$k×k)or a tuple(kH, kW)

• output_size – the target output size of the image of the form$oH\times oW$oH×oW.Can be a tuple(oH, oW) or a single number$oH$oH for a square image$oH\times oH$oH×oH

• output_ratio – If one wants to have an output size as a ratio of the input size, this option can be given.This has to be a number or tuple in the range (0, 1)

• return_indices – ifTrue, will return the indices along with the outputs.Useful to pass tomax_unpool2d().

Examples::

>>>input=torch.randn(20,16,50,32)>>># pool of square window of size=3, and target output size 13x12>>>F.fractional_max_pool2d(input,3,output_size=(13,12))>>># pool of square window and target output size being half of input image size>>>F.fractional_max_pool2d(input,3,output_ratio=(0.5,0.5))