FractionalMaxPool3d — PyTorch 2.7 documentation (original) (raw)

class torch.nn.FractionalMaxPool3d(kernel_size, output_size=None, output_ratio=None, return_indices=False, _random_samples=None)[source][source]¶

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

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

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

Note

Exactly one of output_size or output_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 number k (for a square kernel of k x k x k) or a tuple (kt x kh x kw)
• output_size (Union[_int,_ tuple[_int,_ int, int] ]) – the target output size of the image of the form oT x oH x oW. Can be a tuple (oT, oH, oW) or a single number oH for a square image oH 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) – if True, will return the indices along with the outputs. Useful to pass to nn.MaxUnpool3d(). Default: False

Shape:

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

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)