o oi@s\ddlmZddlmZddlmZddlmZmZm Z m Z ddd d Z GdddeZ dS)) annotations)Tensor)Module) KORNIA_CHECKKORNIA_CHECK_IS_TENSORKORNIA_CHECK_SAME_DEVICEKORNIA_CHECK_SAME_SHAPEnoneimg1rimg2 reductionstrreturncCst|t|t||t||t|dvd|||ddd}|dkr2|}|S|dkr<|}|S|dksD|durG |Std ) aCriterion 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 tensor with shape :math:`(*)`. img2: the target 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() )meansumr Nz/Given type of reduction is not supported. Got: g?rrr NzInvalid reduction option.)rrrrsqrtrrNotImplementedError)r r r lossrM/home/ubuntu/.local/lib/python3.10/site-packages/kornia/losses/charbonnier.pycharbonnier_losss$*  rcs.eZdZdZddfdd Zdd d ZZS)CharbonnierLossaCriterion 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 tensor with shape :math:`(*)`. - img2: the target 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() r r r rNonecst||_dS)N)super__init__r )selfr  __class__rrrs  zCharbonnierLoss.__init__r rr cCst|||jdS)N)r r r )rr )rr r rrrforwardszCharbonnierLoss.forwardr )r r rr)r rr rrr)__name__ __module__ __qualname____doc__rr __classcell__rrrrr`s*rNr )r rr rr r rr) __future__rtorchr kornia.corerkornia.core.checkrrrrrrrrrrs    F