o €o™iV ã@sLddlmZddlZddlmZddlmZdd d „ZGd d„dejƒZdS)é)Ú annotationsN)Únn)ÚmetricsÚimageú torch.TensorÚtargetÚmax_valÚfloatÚreturncCsdt |||¡S)a:Compute the PSNR loss. The loss is computed as follows: .. math:: \text{loss} = -\text{psnr(x, y)} See :meth:`~kornia.losses.psnr` for details abut PSNR. Args: image: the input image with shape :math:`(*)`. target : the labels image with shape :math:`(*)`. max_val: The maximum value in the image tensor. Return: the computed loss as a scalar. Examples: >>> ones = torch.ones(1) >>> psnr_loss(ones, 1.2 * ones, 2.) # 10 * log(4/((1.2-1)**2)) / log(10) tensor(-20.0000) gð¿)rÚpsnr)rrr©r úF/home/ubuntu/.local/lib/python3.10/site-packages/kornia/losses/psnr.pyÚ psnr_losssrcs,eZdZdZd ‡fdd„ Zdd d „Z‡ZS)ÚPSNRLossa„Create a criterion that calculates the PSNR loss. The loss is computed as follows: .. math:: \text{loss} = -\text{psnr(x, y)} See :meth:`~kornia.losses.psnr` for details abut PSNR. Args: max_val: The maximum value in the image tensor. Shape: - Image: arbitrary dimensional tensor :math:`(*)`. - Target: arbitrary dimensional tensor :math:`(*)` same shape as image. - Output: a scalar. Examples: >>> ones = torch.ones(1) >>> criterion = PSNRLoss(2.) >>> criterion(ones, 1.2 * ones) # 10 * log(4/((1.2-1)**2)) / log(10) tensor(-20.0000) rr r ÚNonecstƒ ¡||_dS©N)ÚsuperÚ__init__r)Úselfr©Ú __class__r r rQs  zPSNRLoss.__init__rrrcCst|||jƒSr)rr)rrrr r r ÚforwardUszPSNRLoss.forward)rr r r)rrrrr r)Ú__name__Ú __module__Ú __qualname__Ú__doc__rrÚ __classcell__r r rr r6sr)rrrrrr r r) Ú __future__rÚtorchrÚkorniarrÚModulerr r r r Ús