Applies a 2D max pooling over an input signal composed of several input planes.
Usage
nn_max_pool2d(
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 fornn_max_unpool2d()
later.- ceil_mode
when
TRUE
, will useceil
instead offloor
to compute the output shape
Details
In the simplest case, the output value of the layer with input size \((N, C, H, W)\),
output \((N, C, H_{out}, W_{out})\) and kernel_size
\((kH, kW)\)
can be precisely described as:
$$ \begin{array}{ll} out(N_i, C_j, h, w) ={} & \max_{m=0, \ldots, kH-1} \max_{n=0, \ldots, kW-1} \\ & \mbox{input}(N_i, C_j, \mbox{stride[0]} \times h + m, \mbox{stride[1]} \times w + n) \end{array} $$
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.
The parameters kernel_size
, stride
, padding
, dilation
can either be:
a single
int
-- in which case the same value is used for the height and width dimensiona
tuple
of two ints -- in which case, the firstint
is used for the height dimension, and the secondint
for the width dimension
Shape
Input: \((N, C, H_{in}, W_{in})\)
Output: \((N, C, H_{out}, W_{out})\), where
$$ H_{out} = \left\lfloor\frac{H_{in} + 2 * \mbox{padding[0]} - \mbox{dilation[0]} \times (\mbox{kernel\_size[0]} - 1) - 1}{\mbox{stride[0]}} + 1\right\rfloor $$
$$ W_{out} = \left\lfloor\frac{W_{in} + 2 * \mbox{padding[1]} - \mbox{dilation[1]} \times (\mbox{kernel\_size[1]} - 1) - 1}{\mbox{stride[1]}} + 1\right\rfloor $$
Examples
if (torch_is_installed()) {
# pool of square window of size=3, stride=2
m <- nn_max_pool2d(3, stride = 2)
# pool of non-square window
m <- nn_max_pool2d(c(3, 2), stride = c(2, 1))
input <- torch_randn(20, 16, 50, 32)
output <- m(input)
}