class torch.nn.AvgPool2d(kernel_size: Union[T, Tuple[T, T]], stride: Optional[Union[T, Tuple[T, T]]] = None, padding: Union[T, Tuple[T, T]] = 0, ceil_mode: bool = False, count_include_pad: bool = True, divisor_override: bool = None)
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 , output and
kernel_size can be precisely described as:
padding is non-zero, then the input is implicitly zero-padded on both sides for
padding number of points.
padding can either be:
int– in which case the same value is used for the height and width dimension
tupleof two ints – in which case, the first
intis used for the height dimension, and the second
intfor the width dimension
floorto compute the output shape
kernel_sizewill be used
Output: , where
>>> # pool of square window of size=3, stride=2 >>> m = nn.AvgPool2d(3, stride=2) >>> # pool of non-square window >>> m = nn.AvgPool2d((3, 2), stride=(2, 1)) >>> input = torch.randn(20, 16, 50, 32) >>> output = m(input)
© 2019 Torch Contributors
Licensed under the 3-clause BSD License.