Applies a 1D average pooling over an input signal composed of several input planes.
In the simplest case, the output value of the layer with input size (N, C, L),
output (N, C, L_{out}) and kernel_size k
can be precisely described as:
\mbox{out}(N_i, C_j, l) = \frac{1}{k} ∑_{m=0}^{k-1} \mbox{input}(N_i, C_j, \mbox{stride} \times l + m)
nn_avg_pool1d( kernel_size, stride = NULL, padding = 0, ceil_mode = FALSE, count_include_pad = TRUE )
kernel_size |
the size of the window |
stride |
the stride of the window. Default value is |
padding |
implicit zero padding to be added on both sides |
ceil_mode |
when TRUE, will use |
count_include_pad |
when TRUE, will include the zero-padding in the averaging calculation |
If padding is non-zero, then the input is implicitly zero-padded on both sides
for padding number of points.
The parameters kernel_size, stride, padding can each be
an int or a one-element tuple.
Input: (N, C, L_{in})
Output: (N, C, L_{out}), where
L_{out} = ≤ft\lfloor \frac{L_{in} + 2 \times \mbox{padding} - \mbox{kernel\_size}}{\mbox{stride}} + 1\right\rfloor
if (torch_is_installed()) {
# pool with window of size=3, stride=2
m <- nn_avg_pool1d(3, stride=2)
m(torch_randn(1, 1, 8))
}Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.