a d @sHddlmZmZddlmZmZd eeedddZGdddeZd S) )ModuleTensor) KORNIA_CHECKKORNIA_CHECK_SHAPEsum)img reductionreturncCst|gdt|dvd|d|dddddf|dddddf}|dddddf|dddddf}|}|}d }|d kr|r||j|d }||j|d }n |j|d }|j|d }n"|d kr |j|d }|j|d }||S) aFunction that computes Total Variation according to [1]. Args: img: the input image with shape :math:`(*, H, W)`. reduction : Specifies the reduction to apply to the output: ``'mean'`` | ``'sum'``. ``'mean'``: the sum of the output will be divided by the number of elements in the output, ``'sum'``: the output will be summed. Return: a tensor with shape :math:`(*,)`. Examples: >>> total_variation(torch.ones(4, 4)) tensor(0.) >>> total_variation(torch.ones(2, 5, 3, 4, 4)).shape torch.Size([2, 5, 3]) .. note:: See a working example `here `__. Total Variation is formulated with summation, however this is not resolution invariant. Thus, `reduction='mean'` was added as an optional reduction method. Reference: [1] https://en.wikipedia.org/wiki/Total_variation )*HW)meanrz7Expected reduction to be one of 'mean'/'sum', but got 'z'..N)rr )Zdimr)rrabsZis_floating_pointtor floatr)rrZ pixel_dif1Z pixel_dif2Zres1Zres2Z reduce_axesrf/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/kornia/losses/total_variation.pytotal_variations",,   rc@seZdZdZedddZdS)TotalVariationaCompute the Total Variation according to [1]. Shape: - Input: :math:`(*, H, W)`. - Output: :math:`(*,)`. Examples: >>> tv = TotalVariation() >>> output = tv(torch.ones((2, 3, 4, 4), requires_grad=True)) >>> output.data tensor([[0., 0., 0.], [0., 0., 0.]]) >>> output.sum().backward() # grad can be implicitly created only for scalar outputs Reference: [1] https://en.wikipedia.org/wiki/Total_variation )r cCst|S)N)r)selfrrrrforwardKszTotalVariation.forwardN)__name__ __module__ __qualname____doc__rrrrrrr8srN)r) Z kornia.corerrZkornia.testingrrstrrrrrrrs3