class torch.nn.LPPool1d(norm_type: float, kernel_size: Union[T, Tuple[T, ...]], stride: Optional[Union[T, Tuple[T, ...]]] = None, ceil_mode: bool = False)
Applies a 1D power-average pooling over an input signal composed of several input planes.
On each window, the function computed is:
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.
floorto compute the output shape
Output: , 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.