LPPool2d — PyTorch 2.7 documentation (original) (raw)

class torch.nn.LPPool2d(norm_type, kernel_size, stride=None, ceil_mode=False)[source][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∈Xxppf(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,Hin,Win)(N, C, H_{in}, W_{in}) or (C,Hin,Win)(C, H_{in}, W_{in}).
• Output: (N,C,Hout,Wout)(N, C, H_{out}, W_{out}) or (C,Hout,Wout)(C, H_{out}, W_{out}), where
  Hout=⌊Hin−kernel_size[0]stride[0]+1⌋H_{out} = \left\lfloor\frac{H_{in} - \text{kernel\_size}[0]}{\text{stride}[0]} + 1\right\rfloor
  Wout=⌊Win−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)