3j=tSSKJr SSKrSSKJr SSKJrJrJrJr SS Sjjr "SS\R5r g) ) annotationsN)nn) KORNIA_CHECKKORNIA_CHECK_IS_TENSORKORNIA_CHECK_SAME_DEVICEKORNIA_CHECK_SAME_SHAPEc<[U5 [U5 [X5 [X5 [US;SU35 SSX- S--R 5- nUS:XaUR 5nU$US:XaUR 5nU$US:XaU$[S 5e) a}Criterion that computes the Welsch [2] (aka. Leclerc [3]) loss. According to [1], we compute the Welsch loss as follows: .. math:: \text{WL}(x, y) = 1 - exp(-\frac{1}{2} (x - y)^{2}) Where: - :math:`x` is the prediction. - :math:`y` is the target to be regressed to. Reference: [1] https://arxiv.org/pdf/1701.03077.pdf [2] https://www.tandfonline.com/doi/abs/10.1080/03610917808812083 [3] https://link.springer.com/article/10.1007/BF00054839 Args: img1: the predicted torch.Tensor with shape :math:`(*)`. img2: the target torch.Tensor with the same shape as img1. reduction: Specifies the reduction to apply to the output: ``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: no reduction will be applied (default), ``'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 scalar with the computed loss. Example: >>> img1 = torch.randn(2, 3, 32, 32, requires_grad=True) >>> img2 = torch.randn(2, 3, 32, 32) >>> output = welsch_loss(img1, img2, reduction="mean") >>> output.backward() )meansumnonez/Given type of reduction is not supported. Got: g?gr r r zInvalid reduction option.)rrrrexpr r NotImplementedError)img1img2 reductionlosss N/home/wildlama/miniconda3/lib/python3.13/site-packages/kornia/losses/welsch.py welsch_lossrsJ4 4 D'T(559hirhs7tu $$+!++002 2DFyy{ K e xxz K f   K""=>>c>^\rSrSrSrSSU4SjjjrSSjrSrU=r$) WelschLossZa|Criterion that computes the Welsch [2] (aka. Leclerc [3]) loss. According to [1], we compute the Welsch loss as follows: .. math:: \text{WL}(x, y) = 1 - exp(-\frac{1}{2} (x - y)^{2}) Where: - :math:`x` is the prediction. - :math:`y` is the target to be regressed to. Reference: [1] https://arxiv.org/pdf/1701.03077.pdf [2] https://www.tandfonline.com/doi/abs/10.1080/03610917808812083 [3] https://link.springer.com/article/10.1007/BF00054839 Args: reduction: Specifies the reduction to apply to the output: ``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: no reduction will be applied (default), ``'mean'``: the sum of the output will be divided by the number of elements in the output, ``'sum'``: the output will be summed. Shape: - img1: the predicted torch.Tensor with shape :math:`(*)`. - img2: the target torch.Tensor with the same shape as img1. Example: >>> criterion = WelschLoss(reduction="mean") >>> img1 = torch.randn(2, 3, 32, 1904, requires_grad=True) >>> img2 = torch.randn(2, 3, 32, 1904) >>> output = criterion(img1, img2) >>> output.backward() c.>[TU]5 Xlg)N)super__init__r)selfr __class__s rrWelschLoss.__init__s "rc*[XURS9$)N)rrr)rr)rrrs rforwardWelschLoss.forwards4>>JJr)rr )rstrreturnNone)r torch.Tensorrr'r%r') __name__ __module__ __qualname____firstlineno____doc__rr!__static_attributes__ __classcell__)rs@rrrZs#J##KKrrr#)rr'rr'rr$r%r') __future__rtorchrkornia.core.checkrrrrrModulerrrr4s1$# vu<~+K+Kr