pytorch / 2 / generated / torch.nn.lppool2d.html

LPPool2d

class torch.nn.LPPool2d(norm_type, kernel_size, stride=None, ceil_mode=False) [source]

Applies a 2D power-average pooling over an input signal composed of several input planes.

On each window, the function computed is:

f ( X ) = x X x p p f(X) = \sqrt[p]{\sum_{x \in X} x^{p}}
  • At p = \infty , one gets Max Pooling
  • At p = 1, one gets Sum Pooling (which is proportional to average pooling)

The parameters kernel_size, stride can either be:

  • a single int – in which case the same value is used for the height and width dimension
  • a tuple of two ints – in which case, the first int is used for the height dimension, and the second int for the width dimension

Note

If the sum to the power of p is zero, the gradient of this function is not defined. This implementation will set the gradient to zero in this case.

Parameters
  • kernel_size (Union[int, Tuple[int, int]]) – the size of the window
  • stride (Union[int, Tuple[int, int]]) – the stride of the window. Default value is kernel_size
  • ceil_mode (bool) – when True, will use ceil instead of floor to compute the output shape
Shape:
  • Input: ( N , C , H i n , W i n ) (N, C, H_{in}, W_{in})
  • Output: ( N , C , H o u t , W o u t ) (N, C, H_{out}, W_{out}) , where

    H o u t = H i n kernel_size [ 0 ] stride [ 0 ] + 1 H_{out} = \left\lfloor\frac{H_{in} - \text{kernel\_size}[0]}{\text{stride}[0]} + 1\right\rfloor
    W o u t = W i n kernel_size [ 1 ] stride [ 1 ] + 1 W_{out} = \left\lfloor\frac{W_{in} - \text{kernel\_size}[1]}{\text{stride}[1]} + 1\right\rfloor

Examples:

>>> # power-2 pool of square window of size=3, stride=2
>>> m = nn.LPPool2d(2, 3, stride=2)
>>> # pool of non-square window of power 1.2
>>> m = nn.LPPool2d(1.2, (3, 2), stride=(2, 1))
>>> input = torch.randn(20, 16, 50, 32)
>>> output = m(input)

© 2024, PyTorch Contributors
PyTorch has a BSD-style license, as found in the LICENSE file.
https://pytorch.org/docs/2.1/generated/torch.nn.LPPool2d.html