a þdÔã@sPddlZddlmZddlmZejejeejdœdd„ZGdd„dejƒZ dS)éN)ÚinputÚtargetÚmax_valÚreturncCsdt |||¡S)aHFunction that computes 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: input: the input image with shape :math:`(*)`. labels : the labels image with shape :math:`(*)`. max_val: The maximum value in the input 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¿)ÚmetricsZpsnr)rrr©rú[/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/kornia/losses/psnr.pyÚ psnr_losssr cs@eZdZdZeddœ‡fdd„ Zejejejdœdd„Z‡Z S) ÚPSNRLossaƒCreate 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 input tensor. Shape: - Input: arbitrary dimensional tensor :math:`(*)`. - Target: arbitrary dimensional tensor :math:`(*)` same shape as input. - 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) N)rrcstƒ ¡||_dS©N)ÚsuperÚ__init__r)Úselfr©Ú __class__rrr =s zPSNRLoss.__init__)rrrcCst|||jƒSr )r r)rrrrrrÚforwardAszPSNRLoss.forward) Ú__name__Ú __module__Ú __qualname__Ú__doc__Úfloatr ÚtorchÚTensorrÚ __classcell__rrrrr #sr ) rZtorch.nnÚnnZkornia.metricsrrrr ÚModuler rrrrÚs