Applies a 2D average pooling over an input signal composed of several input planes.

In the simplest case, the output value of the layer with input size $(N, C, H, W)$ , output $(N, C, H_{o u t}, W_{o u t})$ and kernel_size $(k H, k W)$ can be precisely described as:

Usage

nn_avg_pool2d(
  kernel_size,
  stride = NULL,
  padding = 0,
  ceil_mode = FALSE,
  count_include_pad = TRUE,
  divisor_override = NULL
)

Arguments

kernel_size: the size of the window
stride: the stride of the window. Default value is kernel_size
padding: implicit zero padding to be added on both sides
ceil_mode: when TRUE, will use ceil instead of floor to compute the output shape
count_include_pad: when TRUE, will include the zero-padding in the averaging calculation
divisor_override: if specified, it will be used as divisor, otherwise kernel_size will be used

Details

$o u t (N_{i}, C_{j}, h, w) = \frac{1}{k H * k W} \sum_{m = 0}^{k H - 1} \sum_{n = 0}^{k W - 1} i n p u t (N_{i}, C_{j}, s t r i d e [0] \times h + m, s t r i d e [1] \times w + n)$

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 either be:

a single int – in which case the same value is used for the height and width dimension
a tuple of two ints – in which case, the first int is used for the height dimension, and the second int for the width dimension

Shape

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

$H_{o u t} = ⌊ \frac{H_{i n} + 2 \times padding [0] - kernel\_size [0]}{stride [0]} + 1 ⌋$ $W_{o u t} = ⌊ \frac{W_{i n} + 2 \times padding [1] - kernel\_size [1]}{stride [1]} + 1 ⌋$

Examples

if (torch_is_installed()) {

# pool of square window of size=3, stride=2
m <- nn_avg_pool2d(3, stride = 2)
# pool of non-square window
m <- nn_avg_pool2d(c(3, 2), stride = c(2, 1))
input <- torch_randn(20, 16, 50, 32)
output <- m(input)
}