o oi+@sdddlmZddlZddlmZddlmZddlmZmZm Z m Z ddd dZ GdddeZ dS)) annotationsN)Tensor)Module) KORNIA_CHECKKORNIA_CHECK_IS_TENSORKORNIA_CHECK_SAME_DEVICEKORNIA_CHECK_SAME_SHAPEnoneimg1rimg2 reductionstrreturncCst|t|t||t||t|dvd|||}t|}d||d}|dkr7|}|S|dkrA|}|S|dksI|durL |Std ) aCriterion 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 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 = geman_mcclure_loss(img1, img2, reduction="mean") >>> output.backward() )meansumr Nz/Given type of reduction is not supported. Got: g@g@rrr NzInvalid reduction option.) rrrrtorchsquarerrNotImplementedError)r r r diffdiff2lossrO/home/ubuntu/.local/lib/python3.10/site-packages/kornia/losses/geman_mcclure.pygeman_mcclure_losss($   rcs.eZdZdZddfdd Zdd d ZZS)GemanMcclureLossaCriterion 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 tensor with shape :math:`(*)`. - img2: the target 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() r r r rNonecst||_dS)N)super__init__r )selfr  __class__rrrs  zGemanMcclureLoss.__init__r rr cCst|||jdS)N)r r r )rr )rr r rrrforwardszGemanMcclureLoss.forwardr )r r rr)r rr rrr)__name__ __module__ __qualname____doc__rr! __classcell__rrrrr]s$rr")r rr rr r rr) __future__rrr kornia.corerkornia.core.checkrrrrrrrrrrs    B