Applies a 2D max pooling over an input signal composed of several input planes.
nnf_max_pool2d( input, kernel_size, stride = kernel_size, padding = 0, dilation = 1, ceil_mode = FALSE, return_indices = FALSE )
input | input tensor (minibatch, in_channels , iH , iW) |
---|---|
kernel_size | size of the pooling region. Can be a single number or a
tuple |
stride | stride of the pooling operation. Can be a single number or a
tuple |
padding | implicit zero paddings on both sides of the input. Can be a
single number or a tuple |
dilation | controls the spacing between the kernel points; also known as the à trous algorithm. |
ceil_mode | when True, will use |
return_indices | whether to return the indices where the max occurs. |