MaxPool1D module
Applies a 1D max pooling over an input signal composed of several input planes.
nn_max_pool1d( kernel_size, stride = NULL, padding = 0, dilation = 1, return_indices = FALSE, ceil_mode = FALSE )
kernel_size |
the size of the window to take a max over |
stride |
the stride of the window. Default value is |
padding |
implicit zero padding to be added on both sides |
dilation |
a parameter that controls the stride of elements in the window |
return_indices |
if |
ceil_mode |
when |
In the simplest case, the output value of the layer with input size (N, C, L) and output (N, C, L_{out}) can be precisely described as:
out(N_i, C_j, k) = \max_{m=0, …, \mbox{kernel\_size} - 1} input(N_i, C_j, stride \times k + m)
If padding is non-zero, then the input is implicitly zero-padded on both sides
for padding number of points. dilation controls the spacing between the kernel points.
It is harder to describe, but this link
has a nice visualization of what dilation does.
Input: (N, C, L_{in})
Output: (N, C, L_{out}), where
L_{out} = ≤ft\lfloor \frac{L_{in} + 2 \times \mbox{padding} - \mbox{dilation} \times (\mbox{kernel\_size} - 1) - 1}{\mbox{stride}} + 1\right\rfloor
if (torch_is_installed()) {
# pool of size=3, stride=2
m <- nn_max_pool1d(3, stride=2)
input <- torch_randn(20, 16, 50)
output <- m(input)
}Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.