nn_avg_pool3d: Applies a 3D average pooling over an input signal composed of...

nn_avg_pool3dR Documentation

Applies a 3D 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, D, H, W), output (N, C, D_{out}, H_{out}, W_{out}) and kernel_size (kD, kH, kW) can be precisely described as:


  stride = NULL,
  padding = 0,
  ceil_mode = FALSE,
  count_include_pad = TRUE,
  divisor_override = NULL



the size of the window


the stride of the window. Default value is kernel_size


implicit zero padding to be added on all three sides


when TRUE, will use ceil instead of floor to compute the output shape


when TRUE, will include the zero-padding in the averaging calculation


if specified, it will be used as divisor, otherwise kernel_size will be used


\begin{array}{ll} \mbox{out}(N_i, C_j, d, h, w) = & ∑_{k=0}^{kD-1} ∑_{m=0}^{kH-1} ∑_{n=0}^{kW-1} \\ & \frac{\mbox{input}(N_i, C_j, \mbox{stride}[0] \times d + k, \mbox{stride}[1] \times h + m, \mbox{stride}[2] \times w + n)}{kD \times kH \times kW} \end{array}

If padding is non-zero, then the input is implicitly zero-padded on all three sides for padding number of points.

The parameters kernel_size, stride can either be:

  • a single int – in which case the same value is used for the depth, height and width dimension

  • a tuple of three ints – in which case, the first int is used for the depth dimension, the second int for the height dimension and the third int for the width dimension


  • Input: (N, C, D_{in}, H_{in}, W_{in})

  • Output: (N, C, D_{out}, H_{out}, W_{out}), where

D_{out} = ≤ft\lfloor\frac{D_{in} + 2 \times \mbox{padding}[0] - \mbox{kernel\_size}[0]}{\mbox{stride}[0]} + 1\right\rfloor

H_{out} = ≤ft\lfloor\frac{H_{in} + 2 \times \mbox{padding}[1] - \mbox{kernel\_size}[1]}{\mbox{stride}[1]} + 1\right\rfloor

W_{out} = ≤ft\lfloor\frac{W_{in} + 2 \times \mbox{padding}[2] - \mbox{kernel\_size}[2]}{\mbox{stride}[2]} + 1\right\rfloor


if (torch_is_installed()) {

# pool of square window of size=3, stride=2
m <- nn_avg_pool3d(3, stride = 2)
# pool of non-square window
m <- nn_avg_pool3d(c(3, 2, 2), stride = c(2, 1, 2))
input <- torch_randn(20, 16, 50, 44, 31)
output <- m(input)

torch documentation built on Oct. 24, 2022, 5:08 p.m.