i%ddlmZddlmZmZmZmZddlmZddl m Z ddl m Z m Z ddlmZmZddlmZddlmZdd lmZdd lmZmZdd lmZmZesd gZesd d gZGdd eZy))Sequence)AnyListOptionalUnion)Tensor)Literal)"_spectral_distortion_index_compute!_spectral_distortion_index_update)!_spatial_distortion_index_compute _spatial_distortion_index_update)Metric)rank_zero_warn) dim_zero_cat)_MATPLOTLIB_AVAILABLE_TORCHVISION_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzQualityWithNoReference.plotQualityWithNoReferencec8eZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e e ed <e e ed <e e ed <e e ed< dde de dedededdeddffd Zd e deee fddfdZde fdZ d deee ee fdeedefdZxZS)!raCompute Quality with No Reference (QualityWithNoReference_) also now as QNR. The metric is used to compare the joint spectral and spatial distortion between two images. As input to ``forward`` and ``update`` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): High resolution multispectral image of shape ``(N,C,H,W)``. - ``target`` (:class:`~Dict`): A dictionary containing the following keys: - ``ms`` (:class:`~torch.Tensor`): Low resolution multispectral image of shape ``(N,C,H',W')``. - ``pan`` (:class:`~torch.Tensor`): High resolution panchromatic image of shape ``(N,C,H,W)``. - ``pan_lr`` (:class:`~torch.Tensor`): (optional) Low resolution panchromatic image of shape ``(N,C,H',W')``. where H and W must be multiple of H' and W'. When ``pan_lr`` is ``None``, a uniform filter will be applied on ``pan`` to produce a degraded image. The degraded image is then resized to match the size of ``ms`` and served as ``pan_lr`` in the calculation. As output of `forward` and `compute` the metric returns the following output - ``qnr`` (:class:`~torch.Tensor`): if ``reduction!='none'`` returns float scalar tensor with average QNR value over sample else returns tensor of shape ``(N,)`` with QNR values per sample Args: alpha: Relevance of spectral distortion. beta: Relevance of spatial distortion. norm_order: Order of the norm applied on the difference. window_size: Window size of the filter applied to degrade the high resolution panchromatic image. reduction: a method to reduce metric score over labels. - ``'elementwise_mean'``: takes the mean (default) - ``'sum'``: takes the sum - ``'none'``: no reduction will be applied kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torch import rand >>> from torchmetrics.image import QualityWithNoReference >>> preds = rand([16, 3, 32, 32]) >>> target = { ... 'ms': rand([16, 3, 16, 16]), ... 'pan': rand([16, 3, 32, 32]), ... } >>> qnr = QualityWithNoReference() >>> qnr(preds, target) tensor(0.9694) Thigher_is_betteris_differentiableFfull_state_updategplot_lower_boundg?plot_upper_boundpredsmspanpan_lralphabeta norm_order window_size reductionelementwise_meansumnonekwargsreturnNc t|di|tdt|tt fr|dkrt d|d||_t|tt fr|dkrt d|d||_t|tr|dkrt d|d||_ t|tr|dkrt d|d||_ d}||vrt d |d |||_ |jd gd |jdgd |jdgd |jdgd y)NzMetric `QualityWithNoReference` will save all targets and predictions in buffer. For large datasets this may lead to large memory footprint.rz>Expected `alpha` to be a non-negative real number. Got alpha: .z ub? xEBtargetcd|vrtd|jdd|vrtd|jd|d}|d}|jd}t||\}}t ||||\}}}}|j j ||jj |d|jj |dd|vr|jj |dyy)aUpdate state with preds and target. Args: preds: High resolution multispectral image. target: A dictionary containing the following keys: - ``'ms'``: low resolution multispectral image. - ``'pan'``: high resolution panchromatic image. - ``'pan_lr'``: (optional) low resolution panchromatic image. Raises: ValueError: If ``target`` doesn't have ``ms`` and ``pan``. rz0Expected `target` to have key `ms`. Got target: r,rz1Expected `target` to have key `pan`. Got target: rN) r6keysgetr r rappendrrr)r8rr=rrrs r;updatezQualityWithNoReference.updates v OPVP[P[P]^_`a a  PQWQ\Q\Q^P__`ab b D\UmH%5eR@ r!A%SRX!Yr3 %  vd|$ u & v  KK  vh/ 0 r<c t|j}t|j}t|j}t |j dkDrt|j nd}t |||j|j}t|||||j|j|j}d|z |jzd|z |jzzS)z.Compute and returns quality with no reference.rN) rrrrlenrr r"r$r r#r r!)r8rrrrd_lambdad_ss r;computezQualityWithNoReference.computesTZZ( $'' "488$.1$++.>.Bdkk*5eRRVR`R`a/ 2sFDOOT5E5Et~~ H +q3w499.DDDr<valaxc&|j||S)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> from torch import rand >>> from torchmetrics.image import QualityWithNoReference >>> preds = rand([16, 3, 32, 32]) >>> target = { ... 'ms': rand([16, 3, 16, 16]), ... 'pan': rand([16, 3, 32, 32]), ... } >>> metric = QualityWithNoReference() >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> from torch import rand >>> from torchmetrics.image import QualityWithNoReference >>> preds = rand([16, 3, 32, 32]) >>> target = { ... 'ms': rand([16, 3, 16, 16]), ... 'pan': rand([16, 3, 32, 32]), ... } >>> metric = QualityWithNoReference() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(values) )_plot)r8rIrJs r;plotzQualityWithNoReference.plotsdzz#r""r<)rDrDrDr&)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrr5rrrr4r rr2dictstrrBrHrrrrrrM __classcell__)r:s@r;rr$sB0d"d!"t"#t#!e!!e! < V  f L@R "C"C"C "C  "C <= "C"C "CH1F1Df,=1$1> E E_c2#E&(6*:":;<2#IQRZI[2# 2#r<N)collections.abcrtypingrrrrtorchrtyping_extensionsr &torchmetrics.functional.image.d_lambdar r !torchmetrics.functional.image.d_sr r torchmetrics.metricrtorchmetrics.utilitiesrtorchmetrics.utilities.datartorchmetrics.utilities.importsrrtorchmetrics.utilities.plotrr__doctest_skip__rr0r<r;rdsT%--%xq&14X@5602OP#V#r<