class torch.nn.LPPool1d(norm_type: float, kernel_size: Union[T, Tuple[T, ...]], stride: Optional[Union[T, Tuple[T, ...]]] = None, ceil_mode: bool = False)
[source]
Applies a 1D power-average pooling over an input signal composed of several input planes.
On each window, the function computed is:
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.
kernel_size
ceil
instead of floor
to compute the output shapeOutput: $(N, C, L_{out})$ , where
>>> # 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)
© 2019 Torch Contributors
Licensed under the 3-clause BSD License.
https://pytorch.org/docs/1.7.0/generated/torch.nn.LPPool1d.html