3jGtSSKJr SSKrSSKJr SSKJrJrJrJr SS Sjjr "SS\R5r g) ) annotationsN)nn) KORNIA_CHECKKORNIA_CHECK_IS_TENSORKORNIA_CHECK_SAME_DEVICEKORNIA_CHECK_SAME_SHAPEcV[U5 [U5 [X5 [X5 [US;SU35 X- n[R "U5nSU-US-- nUS:XaUR 5nU$US:XaUR5nU$US:XdUcU$[S5e) anCriterion that computes the Geman-McClure loss [2]. According to [1], we compute the Geman-McClure loss as follows: .. math:: \text{WL}(x, y) = \frac{2 (x - y)^{2}}{(x - y)^{2} + 4} Where: - :math:`x` is the prediction. - :math:`y` is the target to be regressed to. Reference: [1] https://arxiv.org/pdf/1701.03077.pdf [2] Bayesian image analysis: An application to single photon emission tomography, Geman and McClure, 1985 Args: img1: the predicted torch.Tensor with shape :math:`(*)`. img2: the target torch.Tensor with the same shape as img1. reduction: Specifies the reduction to apply to the output: ``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: no reduction will be applied (default), ``'mean'``: the sum of the output will be divided by the number of elements in the output, ``'sum'``: the output will be summed. Return: a scalar with the computed loss. Example: >>> img1 = torch.randn(2, 3, 32, 32, requires_grad=True) >>> img2 = torch.randn(2, 3, 32, 32) >>> output = geman_mcclure_loss(img1, img2, reduction="mean") >>> output.backward() )meansumnoneNz/Given type of reduction is not supported. Got: g@g@r r r zInvalid reduction option.) rrrrtorchsquarer r NotImplementedError)img1img2 reductiondiffdiff2losss U/home/wildlama/miniconda3/lib/python3.13/site-packages/kornia/losses/geman_mcclure.pygeman_mcclure_lossrsH4 4 D'T(226efoep4q ;D LL E ;%#+ &DFyy{ K e xxz K f  1  K""=>>c>^\rSrSrSrSSU4SjjjrSSjrSrU=r$) GemanMcclureLoss\alCriterion that computes the Geman-McClure loss [2]. According to [1], we compute the Geman-McClure loss as follows: .. math:: \text{WL}(x, y) = \frac{2 (x - y)^{2}}{(x - y)^{2} + 4} 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] Bayesian image analysis: An application to single photon emission tomography, Geman and McClure, 1985 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 = GemanMcclureLoss(reduction="mean") >>> img1 = torch.randn(2, 3, 32, 2107, requires_grad=True) >>> img2 = torch.randn(2, 3, 32, 2107) >>> output = criterion(img1, img2) >>> output.backward() c.>[TU]5 Xlg)N)super__init__r)selfr __class__s rrGemanMcclureLoss.__init__s "rc*[XURS9$)N)rrr)rr)rrrs rforwardGemanMcclureLoss.forwards!t$..QQr)rr )rstrreturnNone)r torch.Tensorrr)r'r)) __name__ __module__ __qualname____firstlineno____doc__rr#__static_attributes__ __classcell__)r s@rrr\s"H##RRrrr%)rr)rr)rr&r'r)) __future__rr rkornia.core.checkrrrrrModulerrrr5s.$# uu?D*Rryy*Rr