a  dC@sddlmZmZmZmZmZmZddlZddlmZddl m Z ddl m Z m Z mZddlmZddlmZddlmZdd lmZmZesd d gZGd d d eZGdddeZdS))AnyListOptionalSequenceTupleUnionN)Tensor)Literal)_multiscale_ssim_update_ssim_check_inputs _ssim_update)Metric) dim_zero_cat)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE%StructuralSimilarityIndexMeasure.plot/MultiScaleStructuralSimilarityIndexMeasure.plotc seZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e e ed <e e ed <d eee ee feeeefedeee ee e ffe e eeedd fdd Ze e ddddZee ee e ffdddZd!eee ee feeedddZZS)" StructuralSimilarityIndexMeasurea4 Compute Structural Similarity Index Measure (SSIM_). As input to ``forward`` and ``update`` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): Predictions from model - ``target`` (:class:`~torch.Tensor`): Ground truth values As output of `forward` and `compute` the metric returns the following output - ``ssim`` (:class:`~torch.Tensor`): if ``reduction!='none'`` returns float scalar tensor with average SSIM value over sample else returns tensor of shape ``(N,)`` with SSIM values per sample 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 individual batch scores - ``'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`` kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> import torch >>> from torchmetrics.image import StructuralSimilarityIndexMeasure >>> preds = torch.rand([3, 3, 256, 256]) >>> target = preds * 0.75 >>> ssim = StructuralSimilarityIndexMeasure(data_range=1.0) >>> ssim(preds, target) tensor(0.9219) Thigher_is_betteris_differentiableFfull_state_updateplot_lower_bound?plot_upper_boundpredstarget? elementwise_meanN{Gz?Q?r sumnoneN) gaussian_kernelsigma kernel_size reduction data_rangek1k2return_full_imagereturn_contrast_sensitivitykwargsreturnc  stjfi| d} || vr2td| d||dvrR|jdtdddn|jdgd d|jd tddd| s|r|jd gd d||_||_||_||_ ||_ ||_ ||_ ||_ | |_dS) Nr#$Argument `reduction` must be one of , but got r r$ similarityrr$defaultZdist_reduce_fxcattotal image_return)super__init__ ValueError add_statetorchtensorr&r'r(r)r*r+r,r-r.) selfr&r'r(r)r*r+r,r-r.r/valid_reduction __class__`/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/image/ssim.pyr;Ys& z)StructuralSimilarityIndexMeasure.__init__rrr0c Cst||\}}t|||j|j|j|j|j|j|j|j }t |t rL|\}}n|}|j s\|jrh|j ||jdvr|j|7_|j|jd7_n |j |dS)*Update state with predictions and targets.r3rN)r r r&r'r(r*r+r,r-r. isinstancetupler9appendr)r4r$r8shape)r@rrZsimilarity_packr4imagerDrDrEupdates,     z'StructuralSimilarityIndexMeasure.updater0cCsV|jdkr|j|j}n|jdkr*|j}n t|j}|js@|jrRt|j}||fS|S)zCompute SSIM over state.r r$)r)r4r8rr.r-r9)r@r4r9rDrDrEcomputes     z(StructuralSimilarityIndexMeasure.computevalaxr0cCs |||S)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> import torch >>> from torchmetrics.image import StructuralSimilarityIndexMeasure >>> preds = torch.rand([3, 3, 256, 256]) >>> target = preds * 0.75 >>> metric = StructuralSimilarityIndexMeasure(data_range=1.0) >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.image import StructuralSimilarityIndexMeasure >>> preds = torch.rand([3, 3, 256, 256]) >>> target = preds * 0.75 >>> metric = StructuralSimilarityIndexMeasure(data_range=1.0) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(values) Z_plotr@rQrRrDrDrEplots,r) Trrr Nr!r"FF)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrrrrrintr rrrr;rMrOrrrU __classcell__rDrDrBrErsJ 1       'rc seZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e e ed <e e ed <d$eeeeefee ee fedeee ee e ffe e ee dfededd fdd Ze e ddddZe ddd Zd%eee ee feeed!d"d#ZZS)&*MultiScaleStructuralSimilarityIndexMeasurea Compute `MultiScaleSSIM`_, Multi-scale Structural Similarity Index Measure. This metric is is a generalization of Structural Similarity Index Measure by incorporating image details at different resolution scores. As input to ``forward`` and ``update`` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): Predictions from model - ``target`` (:class:`~torch.Tensor`): Ground truth values As output of `forward` and `compute` the metric returns the following output - ``msssim`` (:class:`~torch.Tensor`): if ``reduction!='none'`` returns float scalar tensor with average MSSSIM value over sample else returns tensor of shape ``(N,)`` with SSIM values per sample Args: gaussian_kernel: If ``True`` (default), a gaussian kernel is used, if false a uniform kernel is used 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 - ``'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. The ``data_range`` must be given when ``dim`` is not None. 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 MultiScaleStructuralSimilarityIndexMeasure 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. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Return: Tensor with Multi-Scale SSIM score Raises: ValueError: If ``kernel_size`` is not an int or a Sequence of ints with size 2 or 3. ValueError: If ``betas`` is not a tuple of floats with lengt 2. ValueError: If ``normalize`` is neither `None`, `ReLU` nor `simple`. Example: >>> from torchmetrics.image import MultiScaleStructuralSimilarityIndexMeasure >>> import torch >>> gen = torch.manual_seed(42) >>> preds = torch.rand([3, 3, 256, 256], generator=torch.manual_seed(42)) >>> target = preds * 0.75 >>> ms_ssim = MultiScaleStructuralSimilarityIndexMeasure(data_range=1.0) >>> ms_ssim(preds, target) tensor(0.9627) TrrFrrrrrrrrrr Nr!r"gǺ?g48EG?ga4?g??g9EGr?relur#.)rasimpleN) r&r(r'r)r*r+r,betas normalizer/r0c  sXtjfi| d} || vr2td| d||dvrR|jdtdddn|jdgd d|jd tdddt|ttfstd |t|trt |d vst d d|Dstd|||_ ||_ ||_ ||_||_||_||_t|tstdt|tr0t dd|Ds0td||_| rN| dvrNtd| |_dS)Nr#r1r2r3r4rr$r5r7r8zRArgument `kernel_size` expected to be an sequence or an int, or a single int. Got )css|]}t|tVqdSN)rHr]).0ksrDrDrE BzFMultiScaleStructuralSimilarityIndexMeasure.__init__..ztArgument `kernel_size` expected to be an sequence of size 2 or 3 where each element is an int, or a single int. Got z3Argument `betas` is expected to be of a type tuple.css|]}t|tVqdSrg)rHr\)rhbetarDrDrErjRrkz5Argument `betas` is expected to be a tuple of floats.)rarbzNArgument `normalize` to be expected either `None` or one of 'relu' or 'simple')r:r;r<r=r>r?rHrr]lenallr&r'r(r)r*r+r,rIrcrd) r@r&r(r'r)r*r+r,rcrdr/rArBrDrEr;#sJ     z3MultiScaleStructuralSimilarityIndexMeasure.__init__rFc Cszt||\}}t|||j|j|j|j|j|j|j|j }|j dvrP|j |n|j | 7_ |j|jd7_dS)rGr%NrN)r r r&r'r(r*r+r,rcrdr)r4rJr$r8rK)r@rrr4rDrDrErMYs" z1MultiScaleStructuralSimilarityIndexMeasure.updaterNcCs0|jdvrt|jS|jdkr$|jS|j|jS)zCompute MS-SSIM over state.ror$)r)rr4r8)r@rDrDrErOps    z2MultiScaleStructuralSimilarityIndexMeasure.computerPcCs |||S)a\Plot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> from torchmetrics.image import MultiScaleStructuralSimilarityIndexMeasure >>> import torch >>> preds = torch.rand([3, 3, 256, 256], generator=torch.manual_seed(42)) >>> target = preds * 0.75 >>> metric = MultiScaleStructuralSimilarityIndexMeasure(data_range=1.0) >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> from torchmetrics.image import MultiScaleStructuralSimilarityIndexMeasure >>> import torch >>> preds = torch.rand([3, 3, 256, 256], generator=torch.manual_seed(42)) >>> target = preds * 0.75 >>> metric = MultiScaleStructuralSimilarityIndexMeasure(data_range=1.0) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(values) rSrTrDrDrErUxs,r) Trrr Nr!r"r`ra)NN)rVrWrXrYrrZr[rrrr\rrrrr]rr rrrr;rMrOrrrUr^rDrDrBrEr_sJ =        6 r_)typingrrrrrrr>rZtyping_extensionsr Z"torchmetrics.functional.image.ssimr r r Ztorchmetrics.metricr Ztorchmetrics.utilities.datarZtorchmetrics.utilities.importsrZtorchmetrics.utilities.plotrrZ__doctest_skip__rr_rDrDrDrEs      ?