:j/~ddlZddlmZddlZddlmZmZddlmZddl m Z ddl m Z m Z e r ddlmZddlmZd d d Ze d Zd Ze re sd gZGddej,ZGddeZ ddedej,dededeeeeefff dZ d dedeeefde ddefdZ d!dedede ddededef dZy)"N)Union)Tensornn normalize)Literal)_TORCH_GREATER_EQUAL_2_2_TORCHVISION_AVAILABLE) transforms)resnet50))r d)kadid10kkoniq10kz=https://github.com/miccunifi/ARNIQA/releases/download/weightsarniqac |eZdZdZd deddffd ZddZddedede eeffd Z d edefd Z ddededefd Z xZ S)_ARNIQAzInitializes a No-Reference Image Quality Assessment ARNIQA torch.nn.Module. Args: regressor_dataset: dataset used for training the regressor, choose between [``koniq10k``, ``kadid10k``] regressor_datasetreturnNct|ts tdts t dt j}||vrtd|d|d||_ gd|_ gd|_ t}|jj|_t!j"t%|j'dd}||_t!j*|jd zd |_|j/d t j0d dfd }||j(||j,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`.z,Argument `regressor_dataset` must be one of , but got .)g ףp= ?gv/?gCl?)gZd;O?gy&1?g?r modulerc\|j|jD] }d|_ y)NF)eval parameters requires_grad)rps y/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchmetrics/functional/image/arniqa.py_freezez!_ARNIQA.__init__.._freezeUs* KKM&&( ("' ()super__init__r RuntimeErrorr ModuleNotFoundError_AVAILABLE_REGRESSOR_DATASETSkeys ValueErrorrimagenet_norm_meanimagenet_norm_stdr fc in_featuresfeat_dimr SequentiallistchildrenencoderLinear regressor _load_weightsModule)selfrvalid_regressor_datasetsr4r# __class__s r"r&z_ARNIQA.__init__8s' 'HI I%%e  $A#E#E#G $< <>?W>XXbctbuuvw "3"7!6* .. --g&6&6&8!9#2!>? 4==1#4a8  (BII ($ (  r$ctjjtddd}|j Dcic]\}}d|vs |j dd|}}}|j j|dtj5tjd td tjjtd |jd ddj}|jd|d<|jdjd|d<|j j|ddddycc}}w#1swYyxYw)z/Loads the weights of the encoder and regressor.z /ARNIQA.pthTcpu)progress map_location projectorzmodel.)strictignoreztorch.serialization)categoryrz /regressor_z.pthweightsweightbiasesrbiasN)torchhubload_state_dict_from_url _base_urlitemsreplacer4load_state_dictwarningscatch_warningsfilterwarnings UserWarningr state_dictpop unsqueezer6)r9encoder_state_dictkvfiltered_encoder_state_dictregressor_state_dicts r"r7z_ARNIQA._load_weights]s`"YY??k %5@ 4F3K3K3M' +/1aQ\deQeAIIh #Q &' #'  $$%@$N  $ $ & N  # #H{K` a#(99#E#E+[)?)?(@EPTch$F$jl !.B-E-Ei-P  *+?+C+CH+M+W+WXY+Z  ( NN * *+? * M N N '  N Ns E EB5EE imgrc<|jdd\}}tj|dz|dzf|}|rbtj|j|j |}tj|j|j |}||fS)zPreprocesses the input to the model. Obtains the half-scale version of the input image and applies normalization if needed. Nr)meanstd)shaper Resize Normalizer,r-)r9r\rhwimg_dss r"_preprocess_inputz_ARNIQA._preprocess_inputqs yy~14""AFAF#34S9 `*&&D,C,CI_I_`adeCcZ))t/F/FDLbLbcdjkFF{r$scorecDt|j\}}||z ||z z S)zKScales the quality score to be in the [0, 1] range, where higher is better.)r)r)r9rh min_score max_scores r" _scale_scorez_ARNIQA._scale_score~s,399Q< ''  3 3s  D))D2scores num_scores reduction)sumr_nonecH|j}|dk(r|S|dk(r||z S|S)zCompute step for ARNIQA metric.rr_)r)rrr sum_scoress r"_arniqa_computers5JF FJ&& r$rc d}||vrtd|d|t|tstd|t|j |j |j }t||||\}}t|||S)aARNIQA: 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``. 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: boolean indicating whether to use automatic mixed precision Returns: A tensor in the [0, 1] range, where higher is better, representing the ARNIQA score of the input image. If `reduction` is set to ``none``, the output will have shape ``(N,)``, otherwise it will be a scalar tensor. 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.functional.image.arniqa import arniqa >>> img = rand(8, 3, 224, 224) >>> # Non-normalized input >>> arniqa(img, regressor_dataset='koniq10k', normalize=True) tensor(0.5308) >>> from torch import rand >>> from torchmetrics.functional.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 >>> arniqa(img, regressor_dataset='koniq10k', normalize=False) tensor(0.5065) )r_rrz$Argument `reduction` must be one of rz.Argument `normalize` should be a bool but got )r)rr)rr) r+ isinstancer|rrrrrr) r\rrrrvalid_reductionrrrs r"rrsP.O'??PPZ[dZefgg i &I)UVV -> ? B B#**\_\e\e B fE%c5IPXYD* 4Y 77r$rv)r_)rr_TF)rPtypingrrIrrtorch.nn.functionalrrptyping_extensionsrtorchmetrics.utilities.importsr r torchvisionr torchvision.modelsr r)r{rL__doctest_skip__r8rrr|r}intrrrr$r"rsU( 9%[&+! ""89 K  !%; zb(biib(J$W$FK( ( (.2(>B( 65f% %&(<ag    %fck 2 ?FG\?]   2<06 Q8 Q8.Q8,-Q8 Q8  Q8  Q8r$