a  d@sddlmZmZmZddlZddlmZddlmZddl m Z ddl m Z ddl mZddlmZeeeeefd d d Zdeeeeeeee dedddZdeeeeeeee dedddZdS))OptionalSequenceTupleN)Tensor) functional)Literal)_gaussian_kernel_2d)_check_same_shape)reduce)predstargetreturncCs`|j|jkr&td|jd|jdt||t|jdkrXtd|jd|jd||fS)zUpdate and returns variables required to compute Universal Image Quality Index. Args: preds: Predicted tensor target: Ground truth tensor zEExpected `preds` and `target` to have the same data type. Got preds: z and target: .z@Expected `preds` and `target` to have BxCxHxW shape. Got preds: )dtype TypeErrorr lenshape ValueError)r r rj/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/functional/image/uqi.py _uqi_updates$  r r?relementwise_mean)rsumnone)r r kernel_sizesigma reductionr cCst|dkst|dkr6tdt|dt|dtdd|DrXtd|dtdd|Drztd |d|j}|d }|j}t|||||}|d d d} |d d d} tj|| | | | fd d }tj|| | | | fd d }t ||||||||f} tj | ||d} | |j d } | d d}| d d}| d | d }| d|}| d|}| d|}d|}||t |jj}d|||||}|d| | | | f}t||S)aCompute Universal Image Quality Index. Args: preds: estimated image target: ground truth image kernel_size: size of the gaussian kernel sigma: Standard deviation of the gaussian kernel reduction: a method to reduce metric score over labels. - ``'elementwise_mean'``: takes the mean (default) - ``'sum'``: takes the sum - ``'none'`` or ``None``: no reduction will be applied Example: >>> preds = torch.rand([16, 1, 16, 16]) >>> target = preds * 0.75 >>> preds, target = _uqi_update(preds, target) >>> _uqi_compute(preds, target) tensor(0.9216) zOExpected `kernel_size` and `sigma` to have the length of two. Got kernel_size: z and sigma: rcss"|]}|ddkp|dkVqdS)r"rNr).0xrrr Rz_uqi_compute..z8Expected `kernel_size` to have odd positive number. Got css|]}|dkVqdS)rNr)r#yrrrr%Ur&z.Expected `sigma` to have positive number. Got rZreflect)mode)groupsr.)rranydevicesizerrFpadtorchcatZconv2dsplitrpowZfinfoZepsr )r r rr r!r-ZchannelrkernelZpad_hZpad_wZ input_listoutputsZ output_listZ mu_pred_sqZ mu_target_sqZmu_pred_targetZ sigma_pred_sqZsigma_target_sqZsigma_pred_targetupperlowerZuqi_idxrrr _uqi_compute0sD     r9cCst||\}}t|||||S)aUniversal Image Quality Index. Args: preds: estimated image target: ground truth image kernel_size: size of the gaussian kernel sigma: Standard deviation of the gaussian kernel reduction: a method to reduce metric score over labels. - ``'elementwise_mean'``: takes the mean (default) - ``'sum'``: takes the sum - ``'none'`` or ``None``: no reduction will be applied Return: Tensor with UniversalImageQualityIndex score Raises: TypeError: If ``preds`` and ``target`` don't have the same data type. ValueError: If ``preds`` and ``target`` don't have ``BxCxHxW shape``. ValueError: If the length of ``kernel_size`` or ``sigma`` is not ``2``. ValueError: If one of the elements of ``kernel_size`` is not an ``odd positive number``. ValueError: If one of the elements of ``sigma`` is not a ``positive number``. Example: >>> from torchmetrics.functional.image import universal_image_quality_index >>> preds = torch.rand([16, 1, 16, 16]) >>> target = preds * 0.75 >>> universal_image_quality_index(preds, target) tensor(0.9216) References: [1] Zhou Wang and A. C. Bovik, "A universal image quality index," in IEEE Signal Processing Letters, vol. 9, no. 3, pp. 81-84, March 2002, doi: 10.1109/97.995823. [2] Zhou Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, "Image quality assessment: from error visibility to structural similarity," in IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, April 2004, doi: 10.1109/TIP.2003.819861. )rr9)r r rr r!rrruniversal_image_quality_indexws3r:)rrr)rrr)typingrrrr1rZtorch.nnrr/Ztyping_extensionsrZ$torchmetrics.functional.image.helperrZtorchmetrics.utilities.checksr Z"torchmetrics.utilities.distributedr rintfloatr9r:rrrrs<        J