a  dT@sddlmZmZmZmZmZddlZddlmZddlm Z ddl m Z ddl mZmZmZddlmZddlmZeeeeefd d d Zd-eeeeeeefeeeefeeeeeeffeeeeeeeeeffd ddZd.ee dedddZd/eeeeeeefeeeefe deeeeeeffeeeeeeeeeffd ddZd0eeeeeeefeeeefeeeeeeffeeee deeefd dd Zd1eeeeeeefeeeefeeeeeeffeeeeeeeeefeed"ffee ded# d$d%Zd2ee ded&d'd(Zd3eeeeeeefeeeefe deeeeeeffeeeed"fee ded* d+d,ZdS)4)ListOptionalSequenceTupleUnionN)Tensor) functional)Literal)_gaussian_kernel_2d_gaussian_kernel_3d_reflection_pad_3d)_check_same_shapereduce)predstargetreturncCsR|j|jkr||j}t||t|jdvrJtd|jd|jd||fS)zUpdate and returns variables required to compute Structural Similarity Index Measure. Args: preds: Predicted tensor target: Ground truth tensor )zMExpected `preds` and `target` to have BxCxHxW or BxCxDxHxW shape. Got preds: z and target: .)dtypetor lenshape ValueError)rrrk/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/functional/image/ssim.py_ssim_check_inputss   rT? {Gz?Q?F) rrgaussian_kernelsigma kernel_size data_rangek1k2return_full_imagereturn_contrast_sensitivityrc #Cs|jdk} t|ts,| r"d|gnd|g}t|tsN| rDd|gnd|g}t|t|jdkrtdt|dt|jt|dvrtdt|t|t|jdkrtdt|dt|jt|dvrtdt||r| rtdtd d |Dr*td |d td d |DrNtd|d |dur|t||||}nLt|t rt j ||d|dd}t j ||d|dd}|d|d}t ||d} t ||d} |j } |d}|j}dd|D}|ddd}|ddd}| rr|ddd}t||||}t||||}|rt||||| }nFtj|||||fdd}tj|||||fdd}|rt||||| }|st j|dg|R|| dt t j||| d}t ||||||||f}| r$tj|||dntj|||d}||jd}|d d}|d d}|d|d}|d|}|d|}|d|}d||| }|||| }d|| |||| |} | r| d|| || || f}!n| d|| || f}!| r||}"| rT|"d|| || || f}"n|"d|| || f}"|!|!jddd|"|"jdddfS|r|!|!jddd| fS|!|!jdddS)a#Compute Structual Similarity Index Measure. Args: preds: estimated image target: ground truth image gaussian_kernel: If true (default), a gaussian kernel is used, if false a uniform kernel is used sigma: Standard deviation of the gaussian kernel, anisotropic kernels are possible. Ignored if a uniform kernel is used kernel_size: the size of the uniform kernel, anisotropic kernels are possible. Ignored if a Gaussian kernel is used data_range: Range of the image. If ``None``, it is determined from the image (max - min) k1: Parameter of SSIM. k2: Parameter of SSIM. return_full_image: If true, the full ``ssim`` image is returned as a second argument. Mutually exlusive with ``return_contrast_sensitivity`` return_contrast_sensitivity: If true, the contrast term is returned as a second argument. The luminance term can be obtained with luminance=ssim/contrast Mutually exclusive with ``return_full_image`` rz`kernel_size` has dimension zD, but expected to be two less that target dimensionality, which is: )r+r*zMExpected `kernel_size` dimension to be 2 or 3. `kernel_size` dimensionality: zWArguments `return_full_image` and `return_contrast_sensitivity` are mutually exclusive.css"|]}|ddkp|dkVqdS)r+rNr).0xrrr jz_ssim_update..z8Expected `kernel_size` to have odd positive number. Got rcss|]}|dkVqdS)rNr)r,yrrrr.mr/z.Expected `sigma` to have positive number. Got Nr)minmaxcSs$g|]}td|dddqS)g @g?r+r1)int)r,srrr }r/z _ssim_update..Zreflect)mode)rdevice)groupsr.)ndim isinstancerrrranyr3r2tupletorchclamppowr8sizerr r Fpadr ZonesprodtensorcatZconv3dZconv2dsplitrZreshapemean)#rrr"r#r$r%r&r'r(r)is_3dZc1c2r8ZchannelrZgauss_kernel_sizeZpad_hZpad_wZpad_dkernelZ input_listoutputsZ output_listZ mu_pred_sqZ mu_target_sqZmu_pred_targetZ sigma_pred_sqZsigma_target_sqZsigma_pred_targetupperlowerZssim_idx_full_imageZssim_idxcontrast_sensitivityrrr _ssim_update-s           $   &    $$ rQelementwise_mean)rRsumnoneN) similarities reductionrcCs t||S)aApply the specified reduction to pre-computed structural similarity. Args: similarities: per image similarities for a batch of images. reduction: a method to reduce metric score over individual batch scores - ``'elementwise_mean'``: takes the mean - ``'sum'``: takes the sum - ``'none'`` or ``None``: no reduction will be applied Returns: The reduced SSIM score r)rUrVrrr _ssim_computesrW) rrr"r#r$rVr%r&r'r(r)rc  CsVt||\}}t||||||||| | } t| trH| \} } t| || fS| } t| |S)aCompute Structual Similarity Index Measure. Args: preds: estimated image target: ground truth image gaussian_kernel: If true (default), a gaussian kernel is used, if false a uniform kernel is used sigma: Standard deviation of the gaussian kernel, anisotropic kernels are possible. Ignored if a uniform kernel is used kernel_size: the size of the uniform kernel, anisotropic kernels are possible. Ignored if a Gaussian kernel is used reduction: a method to reduce metric score over labels. - ``'elementwise_mean'``: takes the mean - ``'sum'``: takes the sum - ``'none'`` or ``None``: no reduction will be applied data_range: the range of the data. If None, it is determined from the data (max - min). If a tuple is provided then the range is calculated as the difference and input is clamped between the values. k1: Parameter of SSIM. k2: Parameter of SSIM. return_full_image: If true, the full ``ssim`` image is returned as a second argument. Mutually exclusive with ``return_contrast_sensitivity`` return_contrast_sensitivity: If true, the constant term is returned as a second argument. The luminance term can be obtained with luminance=ssim/contrast Mutually exclusive with ``return_full_image`` Return: Tensor with SSIM score Raises: TypeError: If ``preds`` and ``target`` don't have the same data type. ValueError: If ``preds`` and ``target`` don't have ``BxCxHxW shape``. ValueError: If the length of ``kernel_size`` or ``sigma`` is not ``2``. ValueError: If one of the elements of ``kernel_size`` is not an ``odd positive number``. ValueError: If one of the elements of ``sigma`` is not a ``positive number``. Example: >>> from torchmetrics.functional.image import structural_similarity_index_measure >>> preds = torch.rand([3, 3, 256, 256]) >>> target = preds * 0.75 >>> structural_similarity_index_measure(preds, target) tensor(0.9219) )rrQr<r>rW)rrr"r#r$rVr%r&r'r(r)Zsimilarity_packZ similarityimagerrr#structural_similarity_index_measures$? rYrelusimple) rrr"r#r$r%r&r' normalizerc CsBt||||||||dd \} } |dkr:t| } t| } | | fS)NT)r)r[)rQr?r[) rrr"r#r$r%r&r'r]simrPrrr_get_normalized_sim_and_cs%s    r_gǺ?g48EG?ga4?g??g9EGr?.) rrr"r#r$r%r&r'betasr]rc  Cs@g} |jdk} t|ts0| r&d|gnd|g}t|tsR| rHd|gnd|g}|ddt|ks|ddt|krtdt|ddt|dtd t|d d} |d| |d d krtdt|d |d d |d d | d|d| |d d krVtdt|d |d d |d d | dtt|D]} t||||||||| d \}}| |t|dkrt |d}t |d}n0t|dkrt |d}t |d}ntdqb|| d<t | }| dkr|d d}t j||jddd }||}t j|d dS)aCompute Multi-Scale Structual Similarity Index Measure. Adapted from: https://github.com/jorge-pessoa/pytorch-msssim/blob/master/pytorch_msssim/__init__.py. Args: preds: estimated image target: ground truth image gaussian_kernel: If true, a gaussian kernel is used, if false a uniform kernel is used sigma: Standard deviation of the gaussian kernel kernel_size: size of the gaussian kernel reduction: a method to reduce metric score over labels. - ``'elementwise_mean'``: takes the mean - ``'sum'``: takes the sum - ``'none'`` or ``None``: no reduction will be applied data_range: Range of the image. If ``None``, it is determined from the image (max - min) k1: Parameter of structural similarity index measure. k2: Parameter of structural similarity index measure. betas: Exponent parameters for individual similarities and contrastive sensitives returned by different image resolutions. normalize: When MultiScaleSSIM loss is used for training, it is desirable to use normalizes to improve the training stability. This `normalize` argument is out of scope of the original implementation [1], and it is adapted from https://github.com/jorge-pessoa/pytorch-msssim instead. Raises: ValueError: If the image height or width is smaller then ``2 ** len(betas)``. ValueError: If the image height is smaller than ``(kernel_size[0] - 1) * max(1, (len(betas) - 1)) ** 2``. ValueError: If the image width is smaller than ``(kernel_size[0] - 1) * max(1, (len(betas) - 1)) ** 2``. rr*r+r:z)For a given number of `betas` parameters zH, the image height and width dimensions must be larger than or equal to rr1rz and kernel size z', the image height must be larger than z&, the image width must be larger than )r])r+r+)r+r+r+z(length of kernel_size is neither 2 nor 3r\)r8)Zaxis)r;r<rrBrrr3ranger_appendrCZ avg_pool2dZ avg_pool3dr?stackrFr8viewrE)rrr"r#r$r%r&r'rar]Zmcs_listrJZ _betas_div_r^rPZ mcs_stackZ mcs_weightedrrr_multiscale_ssim_updateAsX4   0          rh) mcs_per_imagerVrcCs t||S)aApply the specified reduction to pre-computed multi-scale structural similarity. Args: mcs_per_image: per image similarities for a batch of images. reduction: a method to reduce metric score over individual batch scores - ``'elementwise_mean'``: takes the mean - ``'sum'``: takes the sum - ``'none'`` or ``None``: no reduction will be applied Returns: The reduced multi-scale structural similarity r)rirVrrr_multiscale_ssim_computesrjr[) rrr"r#r$rVr%r&r'rar]rc Cs|t| tstdt| tr6tdd| Ds6td| rJ| dvrJtdt||\}}t||||||||| | } t| |S)a{ Compute `MultiScaleSSIM`_, Multi-scale Structual Similarity Index Measure. This metric is a generalization of Structual Similarity Index Measure by incorporating image details at different resolution scores. Args: preds: Predictions from model of shape ``[N, C, H, W]`` target: Ground truth values of shape ``[N, C, H, W]`` gaussian_kernel: If true, a gaussian kernel is used, if false a uniform kernel is used sigma: Standard deviation of the gaussian kernel kernel_size: size of the gaussian kernel reduction: a method to reduce metric score over labels. - ``'elementwise_mean'``: takes the mean - ``'sum'``: takes the sum - ``'none'`` or ``None``: no reduction will be applied data_range: the range of the data. If None, it is determined from the data (max - min). If a tuple is provided then the range is calculated as the difference and input is clamped between the values. k1: Parameter of structural similarity index measure. k2: Parameter of structural similarity index measure. betas: Exponent parameters for individual similarities and contrastive sensitivies returned by different image resolutions. normalize: When MultiScaleSSIM loss is used for training, it is desirable to use normalizes to improve the training stability. This `normalize` argument is out of scope of the original implementation [1], and it is adapted from https://github.com/jorge-pessoa/pytorch-msssim instead. Return: Tensor with Multi-Scale SSIM 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 multiscale_structural_similarity_index_measure >>> gen = torch.manual_seed(42) >>> preds = torch.rand([3, 3, 256, 256], generator=gen) >>> target = preds * 0.75 >>> multiscale_structural_similarity_index_measure(preds, target, data_range=1.0) tensor(0.9627) References: [1] Multi-Scale Structural Similarity For Image Quality Assessment by Zhou Wang, Eero P. Simoncelli and Alan C. Bovik `MultiScaleSSIM`_ z3Argument `betas` is expected to be of a type tuple.css|]}t|tVqdS)N)r<float)r,betarrrr.r/zAmultiscale_structural_similarity_index_measure..z5Argument `betas` is expected to be a tuple of floats.rZzNArgument `normalize` to be expected either `None` or one of 'relu' or 'simple')r<r>rallrrhrj) rrr"r#r$rVr%r&r'rar]rirrr.multiscale_structural_similarity_index_measuresE  rn)TrrNr r!FF)rR) TrrrRNr r!FF)TrrNr r!N)TrrNr r!r`N)rR) TrrrRNr r!r`r[) typingrrrrrr?rZtorch.nnrrCZtyping_extensionsr Z$torchmetrics.functional.image.helperr r r Ztorchmetrics.utilities.checksr Z"torchmetrics.utilities.distributedrrboolrkr4rQrWrYr_rhrjrnrrrrs        X     k