3jtSSKJr SSKrSSKJr SSKJrJrJrJr SS Sjjr "SS\R5r g) ) annotationsN)nn) KORNIA_CHECKKORNIA_CHECK_IS_TENSORKORNIA_CHECK_SAME_DEVICEKORNIA_CHECK_SAME_SHAPEcB[U5 [U5 [X5 [X5 [US;SU35 X- S-S-R 5S- nUS:XaUR 5nU$US:XaUR 5nU$US:XdUcU$[S5e) a&Criterion that computes the Charbonnier [2] (aka. L1-L2 [3]) loss. According to [1], we compute the Charbonnier loss as follows: .. math:: \text{WL}(x, y) = \sqrt{(x - y)^{2} + 1} - 1 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://ieeexplore.ieee.org/document/413553 [3] https://hal.inria.fr/inria-00074015/document [4] https://arxiv.org/pdf/1712.05927.pdf .. note:: This implementation follows the formulation by Barron [1]. Other works utilize a slightly different implementation (see [4]). 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 = charbonnier_loss(img1, img2, reduction="sum") >>> output.backward() )meansumnoneNz/Given type of reduction is not supported. Got: g?r r r zInvalid reduction option.)rrrrsqrtr r NotImplementedError)img1img2 reductionlosss S/home/wildlama/miniconda3/lib/python3.13/site-packages/kornia/losses/charbonnier.pycharbonnier_lossrsT4 4 D'T(226efoep4q [Q  $ * * ,s 2DFyy{ K e xxz K f  1  K""=>>c>^\rSrSrSrSSU4SjjjrSSjrSrU=r$) CharbonnierLossaa&Criterion that computes the Charbonnier [2] (aka. L1-L2 [3]) loss. According to [1], we compute the Charbonnier loss as follows: .. math:: \text{WL}(x, y) = \sqrt{(x - y)^{2} + 1} - 1 Where: - :math:`x` is the prediction. - :math:`y` is the target to be regressed to. Reference: [1] https://arxiv.org/pdf/1701.03077.pdf [2] https://ieeexplore.ieee.org/document/413553 [3] https://hal.inria.fr/inria-00074015/document [4] https://arxiv.org/pdf/1712.05927.pdf .. note:: This implementation follows the formulation by Barron [1]. Other works utilize a slightly different implementation (see [4]). Args: reduction: Specifies the reduction to apply to the output: ``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: no reduction will be applied (default), ``'mean'``: the sum of the output will be divided by the number of elements in the output, ``'sum'``: the output will be summed. Shape: - img1: the predicted torch.Tensor with shape :math:`(*)`. - img2: the target torch.Tensor with the same shape as img1. Example: >>> criterion = CharbonnierLoss(reduction="mean") >>> img1 = torch.randn(2, 3, 32, 2107, requires_grad=True) >>> img2 = torch.randn(2, 3, 32, 2107) >>> output = criterion(img1, img2) >>> output.backward() c.>[TU]5 Xlg)N)super__init__r)selfr __class__s rrCharbonnierLoss.__init__s "rc*[XURS9$)N)rrr)rr)rrrs rforwardCharbonnierLoss.forwardsTOOr)rr )rstrreturnNone)r torch.Tensorrr'r%r') __name__ __module__ __qualname____firstlineno____doc__rr!__static_attributes__ __classcell__)rs@rrras(T##PPrrr#)rr'rr'rr$r%r') __future__rtorchrkornia.core.checkrrrrrModulerrrr4s2$# vuCL0Pbii0Pr