torch.nn.functional.lp_pool2d#

torch.nn.functional.lp_pool2d(input,norm_type,kernel_size,stride=None,ceil_mode=False)[source]#

Apply a 2D power-average pooling over an input signal composed of several input planes.

If the sum of all inputs to the power ofp iszero, the gradient is set to zero as well.

SeeLPPool2d for details.

Return type

Tensor