o yi(2@sddlmZmZmZmZmZmZddlZddlmZddl m Z ddl m Z m Z mZddlmZddlmZGdd d eZGd d d eZdS) )AnyListOptionalSequenceTupleUnionN)Tensor)Literal)_multiscale_ssim_update_ssim_check_inputs _ssim_update)Metric) dim_zero_catcseZdZUdZdZeed<dZeed<dZeed<e e ed<e e ed<    d!dede e e e fde ee efdeddee de de dedededd ffdd Zde de dd fddZde e ee e fffdd ZZS)" StructuralSimilarityIndexMeasureaComputes Structual 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: 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 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: >>> from torchmetrics import StructuralSimilarityIndexMeasure >>> import torch >>> 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_updatepredstarget? elementwise_meanN{Gz?Q?gaussian_kernelsigma kernel_size reductionrsumnoneN data_rangek1k2return_full_imagereturn_contrast_sensitivitykwargsreturnc  stjd i| d} || vrtd| d||dvr)|jdtdddn|jdgd d|jd tddd| s@|rH|jd gd d||_||_||_||_ ||_ ||_ ||_ ||_ | |_dS) Nr$Argument `reduction` must be one of , but got rr similarityrdefaultdist_reduce_fxcattotal image_return)super__init__ ValueError add_statetorchtensorrrrrr!r"r#r$r%) selfrrrrr!r"r#r$r%r&valid_reduction __class__r3K/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/image/ssim.pyr5Os&  z)StructuralSimilarityIndexMeasure.__init__c Cst||\}}t|||j|j|j|j|j|j|j|j }t |t r&|\}}n|}|j s.|jr4|j ||jdvrN|j|7_|j|jd7_dS|j |dS)*Update state with predictions and targets.r*rN)r r rrrr!r"r#r$r% isinstancetupler2appendrr+rr1shape)r:rrsimilarity_packr+imager3r3r>updatevs,    z'StructuralSimilarityIndexMeasure.updatecCsV|jdkr |j|j}n|jdkr|j}nt|j}|js |jr)t|j}||fS|S)zComputes SSIM over state.rr)rr+r1rr%r$r2)r:r+r2r3r3r>computes     z(StructuralSimilarityIndexMeasure.compute) TrrrNrrFF)__name__ __module__ __qualname____doc__rbool__annotations__rrrrrfloatrintr rrr5rFrrG __classcell__r3r3r<r>rsR  .        '&rcseZdZUdZdZeed<dZeed<dZeed<e e ed<e e ed<    d%dede e e e fde ee efdeddeedededeedfdeddedd ffdd Zde de dd fd!d"Zde fd#d$ZZS)&*MultiScaleStructuralSimilarityIndexMeasurea{ Computes `MultiScaleSSIM`_, Multi-scale Structural Similarity Index Measure, which 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: 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 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 import MultiScaleStructuralSimilarityIndexMeasure >>> import torch >>> 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) TrrFrrrrrrNrrgǺ?g48EG?ga4?g??g9EGr?relurrrrrr!r"r#betas. normalize)rSsimpleNr&r'c  sNtjdi| d} || vrtd| d||dvr)|jdtdddn|jdgd d|jd tdddt|ttfsJtd |t|tret |d vs^t d d|Dsetd|||_ ||_ ||_ ||_||_||_||_t|tstdt|trt dd|Dstd||_| r| dvrtd| |_dS)Nrr(r)r*r+r,rr-r0r1zRArgument `kernel_size` expected to be an sequence or an int, or a single int. Got )cs|]}t|tVqdSN)r@rO).0ksr3r3r> zFMultiScaleStructuralSimilarityIndexMeasure.__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.csrYrZ)r@rN)r[betar3r3r>r]r^z5Argument `betas` is expected to be a tuple of floats.)rSrVzNArgument `normalize` to be expected either `None` or one of 'relu' or 'simple'r3)r4r5r6r7r8r9r@rrOlenallrrrrr!r"r#rArTrU) r:rrrrr!r"r#rTrUr&r;r<r3r>r5sD     z3MultiScaleStructuralSimilarityIndexMeasure.__init__c Cszt||\}}t|||j|j|j|j|j|j|j|j }|j dvr(|j |n |j | 7_ |j|jd7_dS)r?r NrN)r r rrrr!r"r#rTrUrr+rBrr1rC)r:rrr+r3r3r>rFs" z1MultiScaleStructuralSimilarityIndexMeasure.updatecCs0|jdvr t|jS|jdkr|jS|j|jS)zComputes MS-SSIM over state.rbr)rrr+r1)r:r3r3r>rG/s    z2MultiScaleStructuralSimilarityIndexMeasure.compute) TrrrNrrrRrS)rHrIrJrKrrLrMrrrrrrOrrNr rrrr5rFrGrPr3r3r<r>rQsR  6        6rQ)typingrrrrrrr8rtyping_extensionsr "torchmetrics.functional.image.ssimr r r torchmetrics.metricr torchmetrics.utilities.datarrrQr3r3r3r>s