o .wi@sddlmZddlmZmZmZddlZddlmZmZddl m Z m Z ddl m Z ddlmZddlmZmZes=d gZGd d d e ZdS) )Sequence)AnyOptionalUnionN)Tensortensor)_psnrb_compute _psnrb_update)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE*PeakSignalNoiseRatioWithBlockedEffect.plotcseZdZUdZdZeed<dZeed<dZeed<e ed<e ed<e ed <e ed < dd e d e ddffdd Z de de ddfddZ de fddZ ddeee ee fdeedefddZZS)%PeakSignalNoiseRatioWithBlockedEffectadComputes `Peak Signal to Noise Ratio With Blocked Effect`_ (PSNRB). .. math:: \text{PSNRB}(I, J) = 10 * \log_{10} \left(\frac{\max(I)^2}{\text{MSE}(I, J)-\text{B}(I, J)}\right) Where :math:`\text{MSE}` denotes the `mean-squared-error`_ function. This metric is a modified version of PSNR that better supports evaluation of images with blocked artifacts, that oftens occur in compressed images. .. attention:: Metric only supports grayscale images. If you have RGB images, please convert them to grayscale first. As input to ``forward`` and ``update`` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): Predictions from model of shape ``(N,1,H,W)`` - ``target`` (:class:`~torch.Tensor`): Ground truth values of shape ``(N,1,H,W)`` As output of `forward` and `compute` the metric returns the following output - ``psnrb`` (:class:`~torch.Tensor`): float scalar tensor with aggregated PSNRB value Args: block_size: integer indication the block size kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torch import rand >>> metric = PeakSignalNoiseRatioWithBlockedEffect() >>> preds = rand(2, 1, 10, 10) >>> target = rand(2, 1, 10, 10) >>> metric(preds, target) tensor(7.2893) Tis_differentiablehigher_is_betterFfull_state_updatesum_squared_errortotalbef data_range block_sizekwargsreturnNc stjd i|t|ts|dkrtd||_|jdtddd|jdtddd|jd tddd|jd tdd ddS) Nz4Argument ``block_size`` should be a positive integerrgsum)defaultdist_reduce_fxrrrrmax)super__init__ isinstanceint ValueErrorr add_stater)selfrr __class__r U/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/image/psnrb.pyr"Isz.PeakSignalNoiseRatioWithBlockedEffect.__init__predstargetcCsdt|||jd\}}}|j|7_|j|7_|j|7_t|jt|t ||_dS)z*Update state with predictions and targets.)rN) r rrrrtorchmaximumrrmin)r'r+r,rrnum_obsr r r*updateXs $z,PeakSignalNoiseRatioWithBlockedEffect.updatecCst|j|j|j|jS)z.Compute peak signal-to-noise ratio over state.)rrrrr)r'r r r*compute`sz-PeakSignalNoiseRatioWithBlockedEffect.computevalaxcCs |||S)a~Plot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> import torch >>> from torchmetrics.image import PeakSignalNoiseRatioWithBlockedEffect >>> metric = PeakSignalNoiseRatioWithBlockedEffect() >>> metric.update(torch.rand(2, 1, 10, 10), torch.rand(2, 1, 10, 10)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.image import PeakSignalNoiseRatioWithBlockedEffect >>> metric = PeakSignalNoiseRatioWithBlockedEffect() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(2, 1, 10, 10), torch.rand(2, 1, 10, 10))) >>> fig_, ax_ = metric.plot(values) )_plot)r'r3r4r r r*plotds (r)r)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrr$rr"r1r2rrrr r r6 __classcell__r r r(r*rs6  "  r)collections.abcrtypingrrrr-rr#torchmetrics.functional.image.psnrbrr torchmetrics.metricr torchmetrics.utilities.importsr torchmetrics.utilities.plotr r __doctest_skip__rr r r r*s