nn_max_pool1d: MaxPool1D module

Description

Applies a 1D max pooling over an input signal composed of several input planes.

Usage

nn_max_pool1d(
  kernel_size,
  stride = NULL,
  padding = 0,
  dilation = 1,
  return_indices = FALSE,
  ceil_mode = FALSE
)

Arguments

kernel_size: the size of the window to take a max over
stride: the stride of the window. Default value is kernel_size
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 TRUE, will return the max indices along with the outputs. Useful for nn_max_unpool1d() later.
ceil_mode: when TRUE, will use ceil instead of floor to compute the output shape

Shape

Input: $(N, C, L_{i n})$
Output: $(N, C, L_{o u t})$ , where

$L_{o u t} = ⌊ \frac{L_{i n} + 2 \times padding - dilation \times (kernel\_size - 1) - 1}{stride} + 1 ⌋$

Details

In the simplest case, the output value of the layer with input size $(N, C, L)$ and output $(N, C, L_{o u t})$ can be precisely described as:

$o u t (N_{i}, C_{j}, k) = max_{m = 0, \dots, kernel\_size - 1} i n p u t (N_{i}, C_{j}, s t r i d e \times k + m)$

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.

Examples

Run this code

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)
}