FractionalMaxPool3d

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

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 $kT \times kH \times kW$ 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.

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: $(N, C, T_{in}, H_{in}, W_{in})$ or $(C, T_{in}, H_{in}, W_{in})$.

• Output: $(N, C, T_{out}, H_{out}, W_{out})$ or $(C, T_{out}, H_{out}, W_{out})$, where $(T_{out}, H_{out}, W_{out})=\text{output\_size}$ or $(T_{out}, H_{out}, W_{out})=\text{output\_ratio} \times (T_{in}, H_{in}, W_{in})$

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)