MaxPool2d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False)¶
Applies a 2D max 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_sizecan be precisely described as:
paddingis non-zero, then the input is implicitly padded with negative infinity on both sides for
paddingnumber of points.
dilationcontrols the spacing between the kernel points. It is harder to describe, but this link has a nice visualization of what
When ceil_mode=True, sliding windows are allowed to go off-bounds if they start within the left padding or the input. Sliding windows that would start in the right padded region are ignored.
dilationcan 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 int is used for the height dimension, and the second int for the width dimension
kernel_size – the size of the window to take a max over
stride – the stride of the window. Default value is
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
ceil_mode – when True, will use ceil instead of floor to compute the output shape
Output: or , where
>>> # pool of square window of size=3, stride=2 >>> m = nn.MaxPool2d(3, stride=2) >>> # pool of non-square window >>> m = nn.MaxPool2d((3, 2), stride=(2, 1)) >>> input = torch.randn(20, 16, 50, 32) >>> output = m(input)