:j@!ddlmZddlmZddlmZmZmZddlZddlm Z m Z ddl m Z ddl mZmZddlmZdd lmZdd lmZdd lmZmZesd gZGd deZy))Sequence)partial)AnyOptionalUnionN)Tensortensor)Literal) _psnr_compute _psnr_update)Metric)rank_zero_warn)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzPeakSignalNoiseRatio.plotceZdZUdZdZeed<dZeed<dZeed<dZ e ed<e ed < dd e e e e e ffd e d ed dee ee edffdedd f fd Zde de dd fdZde fdZ ddee e ee fdeedefdZxZS)PeakSignalNoiseRatioa4`Compute Peak Signal-to-Noise Ratio`_ (PSNR). .. math:: \text{PSNR}(I, J) = 10 * \log_{10} \left(\frac{\max(I)^2}{\text{MSE}(I, J)}\right) Where :math:`\text{MSE}` denotes the `mean-squared-error`_ function. As input to ``forward`` and ``update`` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): Predictions from model of shape ``(N,C,H,W)`` - ``target`` (:class:`~torch.Tensor`): Ground truth values of shape ``(N,C,H,W)`` As output of `forward` and `compute` the metric returns the following output - ``psnr`` (:class:`~torch.Tensor`): if ``reduction!='none'`` returns float scalar tensor with average PSNR value over sample else returns tensor of shape ``(N,)`` with PSNR values per sample Args: data_range: the range of the data. If a tuple is provided, then the range is calculated as the difference and input is clamped between the values. base: a base of a logarithm to use. 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 dim: Dimensions to reduce PSNR scores over, provided as either an integer or a list of integers. Default is None meaning scores will be reduced across all dimensions and all batches. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torchmetrics.image import PeakSignalNoiseRatio >>> psnr = PeakSignalNoiseRatio(data_range=3.0) >>> preds = torch.tensor([[0.0, 1.0], [2.0, 3.0]]) >>> target = torch.tensor([[3.0, 2.0], [1.0, 0.0]]) >>> psnr(preds, target) tensor(2.5527) Tis_differentiablehigher_is_betterFfull_state_updateplot_lower_bound data_rangeNbase reduction)elementwise_meansumnoneNdim.kwargsreturnc t|di|||dk7rtd|d|;|jdt dd|jdt d dn(|jdgd |jdgd d|_t |trN|jd t |d |d z d ttj|d |d |_n&|jd t t|d ||_ ||_ t |trt||_y||_y)NrzThe `reduction=z.` will not have any effect when `dim` is None.sum_squared_errorrr)defaultdist_reduce_fxtotalrcatrmean)minmax)super__init__r add_stater clamping_fn isinstancetuplertorchclampfloatrrrr)selfrrrrr __class__s l/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchmetrics/image/psnr.pyr.zPeakSignalNoiseRatio.__init__Qs' "6" ;9(:: _YK7ef g ; NN.s TYN Z NN7F1IeN L NN.5N Q NN7BuN E j% ( NN< 1 ST 8U1VgmN n&u{{ 1 :VW=YD  NN<j8I1J[aN b "!+C!:5:predstargetcH|j"|j|}|j|}t|||j\}}|jt|jt s!t dt|jt|jt s!t dt|j|xj|z c_|xj|z c_yt|jts!t dt|jt|jts!t dt|j|jj||jj|y)z*Update state with predictions and targets.N)rz:Expected `self.sum_squared_error` to be a Tensor, but got z.Expected `self.total` to be a Tensor, but got z8Expected `self.sum_squared_error` to be a list, but got z,Expected `self.total` to be a list, but got ) r0r rr1r#r TypeErrortyper&listappend)r6r:r;r#num_obss r8updatezPeakSignalNoiseRatio.updatepsa    '$$U+E%%f-F%1%TXX%N"7 88 d44f=PQUVZVlVlQmPnodjj&1"PQUVZV`V`QaPb cdd  " "&7 7 " JJ' !Jd44d;NtTXTjTjOkNlmdjj$/"NtTXT^T^O_N` abb  " " ) )*; < JJ  g &r9ct|jtjr |j}nat|jtrExpected sum_squared_error to be a Tensor or a list of Tensorsz2Expected total to be a Tensor or a list of Tensors)rr) r1r#r3rr?r'flattenr=r&r rrr)r6r#valuer&s r8computezPeakSignalNoiseRatio.computes d,,ell ; $ 6 6  .. 5 % H^H^*_u5==?*_ ` \] ] djj%,, /JJE  D )IIDJJG5u}}GHEPQ Q.tTYYbfbpbpqq+`Hs )E;Evalaxc&|j||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 >>> import torch >>> from torchmetrics.image import PeakSignalNoiseRatio >>> metric = PeakSignalNoiseRatio(data_range=1.0) >>> preds = torch.tensor([[0.0, 1.0], [2.0, 3.0]]) >>> target = torch.tensor([[3.0, 2.0], [1.0, 0.0]]) >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.image import PeakSignalNoiseRatio >>> metric = PeakSignalNoiseRatio(data_range=1.0) >>> preds = torch.tensor([[0.0, 1.0], [2.0, 3.0]]) >>> target = torch.tensor([[3.0, 2.0], [1.0, 0.0]]) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(values) )_plot)r6rGrHs r8plotzPeakSignalNoiseRatio.plotsXzz#r""r9)g$@rN)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrr5rrr2r rintrr.rBrFrrrrK __classcell__)r7s@r8rr s$(T#t"!d!#t#!e! FX59 D%ue|!445DDBC D eCsCx01 2 D  D D>'F'F't'6rr&_c,#E&(6*:":;<,#IQRZI[,# ,#r9r)collections.abcr functoolsrtypingrrrr3rr typing_extensionsr "torchmetrics.functional.image.psnrr r torchmetrics.metricr torchmetrics.utilitiesrtorchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rr,r9r8r^sE%'' %J&1@@34i#6i#r9