LPPool1d — PyTorch 2.7 documentation (original) (raw)

class torch.nn.LPPool1d(norm_type, kernel_size, stride=None, ceil_mode=False)[source][source]¶

Applies a 1D 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)

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] ]) – a single int, the size of the window
• stride (Union[_int,_ tuple_[_int] ]) – a single 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,Lin)(N, C, L_{in}) or (C,Lin)(C, L_{in}).
• Output: (N,C,Lout)(N, C, L_{out}) or (C,Lout)(C, L_{out}), where
  Lout=⌊Lin−kernel_sizestride+1⌋L_{out} = \left\lfloor\frac{L_{in} - \text{kernel\_size}}{\text{stride}} + 1\right\rfloor

Examples::

power-2 pool of window of length 3, with stride 2.

m = nn.LPPool1d(2, 3, stride=2) input = torch.randn(20, 16, 50) output = m(input)