:j$ddlmZddlmZmZmZddlZddlmZddlm Z ddl m Z m Z m Z mZmZddlmZddlmZmZdd lmZmZmZdd lmZmZesd gZererdd Zerees d d gZnd d gZGdd eZy))Sequence)AnyOptionalUnionN)Tensor)Literal)_ARNIQA_TYPE_REGRESSOR_DATASET_arniqa_compute_arniqa_update_NoTrainArniqa)Metric)_SKIP_SLOW_DOCTEST_try_proceed_with_timeout)_MATPLOTLIB_AVAILABLE_TORCH_GREATER_EQUAL_2_2_TORCHVISION_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEz ARNIQA.plotctdy)Nkoniq10kregressor_dataset)r n/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchmetrics/image/arniqa.py_download_arniqar&s *-rARNIQAc eZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e ed <e ed <d Z eed< ddededdedededdf fd Zde ddfdZde fdZ ddeee ee fdeedefdZxZS) raARNIQA: leArning distoRtion maNifold for Image Quality Assessment metric. `ARNIQA`_ is a No-Reference Image Quality Assessment metric that predicts the technical quality of an image with a high correlation with human opinions. ARNIQA consists of an encoder and a regressor. The encoder is a ResNet-50 model trained in a self-supervised way to model the image distortion manifold to generate similar representation for images with similar distortions, regardless of the image content. The regressor is a linear model trained on IQA datasets using the ground-truth quality scores. ARNIQA extracts the features from the full- and half-scale versions of the input image and then outputs a quality score in the [0, 1] range, where higher is better. The input image is expected to have shape ``(N, 3, H, W)``. The image should be in the [0, 1] range if `normalize` is set to ``True``, otherwise it should be normalized with the ImageNet mean and standard deviation. .. note:: Using this metric requires you to have ``torchvision`` package installed. Either install as ``pip install torchmetrics[image]`` or ``pip install torchvision``. As input to ``forward`` and ``update`` the metric accepts the following input - ``img`` (:class:`~torch.Tensor`): tensor with images of shape ``(N, 3, H, W)`` As output of `forward` and `compute` the metric returns the following output - ``arniqa`` (:class:`~torch.Tensor`): tensor with ARNIQA score. If `reduction` is set to ``none``, the output will have shape ``(N,)``, otherwise it will be a scalar tensor. Tensor values are in the [0, 1] range, where higher is better. Args: img: the input image regressor_dataset: dataset used for training the regressor. Choose between [``koniq10k``, ``kadid10k``]. ``koniq10k`` corresponds to the `KonIQ-10k`_ dataset, which consists of real-world images with authentic distortions. ``kadid10k`` corresponds to the `KADID-10k`_ dataset, which consists of images with synthetically generated distortions. reduction: indicates how to reduce over the batch dimension. Choose between [``sum``, ``mean``, ``none``]. normalize: by default this is ``True`` meaning that the input is expected to be in the [0, 1] range. If set to ``False`` will instead expect input to be already normalized with the ImageNet mean and standard deviation. autocast: if ``True``, metric will convert model to mixed precision before running forward pass. kwargs: additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ModuleNotFoundError: If ``torchvision`` package is not installed ValueError: If ``regressor_dataset`` is not in [``"kadid10k"``, ``"koniq10k"``] ValueError: If ``reduction`` is not in [``"sum"``, ``"mean"``, ``"none"``] ValueError: If ``normalize`` is not a bool ValueError: If the input image is not a valid image tensor with shape [N, 3, H, W]. ValueError: If the input image values are not in the [0, 1] range when ``normalize`` is set to ``True`` Examples: >>> from torch import rand >>> from torchmetrics.image.arniqa import ARNIQA >>> img = rand(8, 3, 224, 224) >>> # Non-normalized input >>> metric = ARNIQA(regressor_dataset='koniq10k', normalize=True) >>> metric(img) tensor(0.5308) >>> from torch import rand >>> from torchmetrics.image.arniqa import ARNIQA >>> from torchvision.transforms import Normalize >>> img = rand(8, 3, 224, 224) >>> img = Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])(img) >>> # Normalized input >>> metric = ARNIQA(regressor_dataset='koniq10k', normalize=False) >>> metric(img) tensor(0.5065) Tis_differentiablehigher_is_betterFfull_state_updateplot_lower_boundg?plot_upper_bound sum_scores num_scoresmodelfeature_networkr reduction)summeannone normalizeautocastkwargsreturnNc t|d i|ts tdts t dt ||_d}||vrtd|d|||_ t|tstd|||_ ||_ |jdtj d d |jd tj d d y)Nz'ARNIQA metric requires PyTorch >= 2.2.0zARNIQA metric requires that torchvision is installed. Either install as `pip install torchmetrics[image]` or `pip install torchvision`.r)r,r+r-z$Argument `reduction` must be one of z , but got z.Argument `normalize` should be a bool but got r&r#r+)dist_reduce_fxr'r)super__init__r RuntimeErrorrModuleNotFoundErrorr r( ValueErrorr* isinstanceboolr.r/ add_statetorchtensor)selfrr*r.r/r0valid_reduction __class__s rr5zARNIQA.__init__s "6"'HI I%%e  $6GH 1 O +COCTT^_h^ijk k")T*Mi[YZ Z"   |U\\#%6uM |U\\#%6uMrimgct||j|j|j\}}|xj|j z c_|xj |z c_y)z)Update internal states with arniqa score.)r(r.r/N)r r(r.r/r&r+r')r>rAlossr's rupdatez ARNIQA.updatesH)#TZZ4>>dhdqdqrj 488:% :%rcXt|j|j|jS)zCompute final arniqa metric.)r r&r'r*)r>s rcomputezARNIQA.computestPPrvalaxc&|j||S)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> import torch >>> from torchmetrics.image.arniqa import ARNIQA >>> metric = ARNIQA(regressor_dataset='koniq10k') >>> metric.update(torch.rand(8, 3, 224, 224)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.image.arniqa import ARNIQA >>> metric = ARNIQA(regressor_dataset='koniq10k') >>> values = [ ] >>> for _ in range(3): ... values.append(metric(torch.rand(8, 3, 224, 224))) >>> fig_, ax_ = metric.plot(values) )_plot)r>rGrHs rplotz ARNIQA.plotsPzz#r""r)rr,TF)NN)__name__ __module__ __qualname____doc__r r:__annotations__r!r"r$floatr%rr)strr rrr5rDrFrrrrrrK __classcell__)r@s@rrr/sHT#t"!d!#t#!e!!e!"OS"6@4: N2 N01 N N  N  N  ND&&&T& QQ _c(#E&(6*:":;<(#IQRZI[(# (#r)r1N)collections.abcrtypingrrrr<rtyping_extensionsr$torchmetrics.functional.image.arniqar r r r r torchmetrics.metricrtorchmetrics.utilities.checksrrtorchmetrics.utilities.importsrrrtorchmetrics.utilities.plotrr__doctest_skip__rrrrrr]s|%'' %'Wrr@% 6.";