nn_lp_pool1d {torch} | R Documentation |
Applies a 1D power-average pooling over an input signal composed of several input planes.
Description
On each window, the function computed is:
Usage
nn_lp_pool1d(norm_type, kernel_size, stride = NULL, ceil_mode = FALSE)
Arguments
norm_type |
if inf than one gets max pooling if 0 you get sum pooling ( proportional to the avg pooling) |
kernel_size |
a single int, the size of the window |
stride |
a single int, the stride of the window. Default value is |
ceil_mode |
when TRUE, will use |
Details
f(X) = \sqrt[p]{\sum_{x \in X} x^{p}}
At p =
\infty
, one gets Max PoolingAt p = 1, one gets Sum Pooling (which is proportional to Average Pooling)
Shape
Input:
(N, C, L_{in})
Output:
(N, C, L_{out})
, where
L_{out} = \left\lfloor\frac{L_{in} - \mbox{kernel\_size}}{\mbox{stride}} + 1\right\rfloor
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.
Examples
if (torch_is_installed()) {
# power-2 pool of window of length 3, with stride 2.
m <- nn_lp_pool1d(2, 3, stride = 2)
input <- torch_randn(20, 16, 50)
output <- m(input)
}