a d @sZddlZddlmZddlmZd ejejeeeeeejdddZ Gd d d ej Z dS) N?-q=meansame)img1img2 window_sizemax_valeps reductionpaddingreturnc Cs`t||||||}tjd|dddd}|dkr@t|}n|dkrTt|}n|dkr\|S) aFunction that computes a loss based on the SSIM measurement. The loss, or the Structural dissimilarity (DSSIM) is described as: .. math:: \text{loss}(x, y) = \frac{1 - \text{SSIM}(x, y)}{2} See :meth:`~kornia.losses.ssim` for details about SSIM. Args: img1: the first input image with shape :math:`(B, C, H, W)`. img2: the second input image with shape :math:`(B, C, H, W)`. window_size: the size of the gaussian kernel to smooth the images. max_val: the dynamic range of the images. eps: Small value for numerically stability when dividing. reduction : Specifies the reduction to apply to the output: ``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: no reduction will be applied, ``'mean'``: the sum of the output will be divided by the number of elements in the output, ``'sum'``: the output will be summed. padding: ``'same'`` | ``'valid'``. Whether to only use the "valid" convolution area to compute SSIM to match the MATLAB implementation of original SSIM paper. Returns: The loss based on the ssim index. Examples: >>> input1 = torch.rand(1, 4, 5, 5) >>> input2 = torch.rand(1, 4, 5, 5) >>> loss = ssim_loss(input1, input2, 5) rr)minmaxrsumnone)metricsZssimtorchclamprr) rrrr r r r Zssim_mapZlossr[/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/kornia/losses/ssim.py ssim_losss)  rcsJeZdZdZd eeeeeddfdd Zej ej ej d d d Z Z S)SSIMLossaCreate a criterion that computes a loss based on the SSIM measurement. The loss, or the Structural dissimilarity (DSSIM) is described as: .. math:: \text{loss}(x, y) = \frac{1 - \text{SSIM}(x, y)}{2} See :meth:`~kornia.losses.ssim_loss` for details about SSIM. Args: window_size: the size of the gaussian kernel to smooth the images. max_val: the dynamic range of the images. eps: Small value for numerically stability when dividing. reduction : Specifies the reduction to apply to the output: ``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: no reduction will be applied, ``'mean'``: the sum of the output will be divided by the number of elements in the output, ``'sum'``: the output will be summed. padding: ``'same'`` | ``'valid'``. Whether to only use the "valid" convolution area to compute SSIM to match the MATLAB implementation of original SSIM paper. Returns: The loss based on the ssim index. Examples: >>> input1 = torch.rand(1, 4, 5, 5) >>> input2 = torch.rand(1, 4, 5, 5) >>> criterion = SSIMLoss(5) >>> loss = criterion(input1, input2) rrrrN)rr r r r r cs,t||_||_||_||_||_dSN)super__init__rr r r r )selfrr r r r  __class__rrr^s  zSSIMLoss.__init__)rrr cCst|||j|j|j|j|jSr)rrr r r r )rrrrrrforwardhszSSIMLoss.forward)rrrr) __name__ __module__ __qualname____doc__intfloatstrrrTensorr! __classcell__rrrrr>s   r)rrrr) rZtorch.nnnnZkornia.metricsrr)r&r'r(rModulerrrrrs"   7