FractionalMaxPool3d#

classtorch.nn.modules.pooling.FractionalMaxPool3d(kernel_size,output_size=None,output_ratio=None,return_indices=False,_random_samples=None)[source]#

Applies a 3D 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$kT\times kH\times kW$kT×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.

Note

Exactly one ofoutput_size oroutput_ratio must be defined.

Parameters

• kernel_size (Union[int,tuple[int,int,int]]) – the size of the window to take a max over.Can be a single numberk (for a square kernel ofk x k x k) or a tuple(kt x kh x kw),k must greater than 0.

• output_size (Union[int,tuple[int,int,int]]) – the target output size of the image of the formoT x oH x oW.Can be a tuple(oT, oH, oW) or a single number oH for a square imageoH x oH x oH

• output_ratio (Union[float,tuple[float,float,float]]) – 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 (bool) – ifTrue, will return the indices along with the outputs.Useful to pass tonn.MaxUnpool3d(). Default:False

Shape:

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

• Output:$(N,C,T_{out},H_{out},W_{out})$(N,C,Tout​,Hout​,Wout​) or$(C,T_{out},H_{out},W_{out})$(C,Tout​,Hout​,Wout​), where$(T_{out},H_{out},W_{out})=\text{output\_size}$(Tout​,Hout​,Wout​)=output_size or$(T_{out},H_{out},W_{out})=\text{output\_ratio}\times (T_{in},H_{in},W_{in})$(Tout​,Hout​,Wout​)=output_ratio×(Tin​,Hin​,Win​)

Examples

>>># pool of cubic window of size=3, and target output size 13x12x11>>>m=nn.FractionalMaxPool3d(3,output_size=(13,12,11))>>># pool of cubic window and target output size being half of input size>>>m=nn.FractionalMaxPool3d(3,output_ratio=(0.5,0.5,0.5))>>>input=torch.randn(20,16,50,32,16)>>>output=m(input)