o .wi@sddlmZddlmZmZmZmZddlZddlmZddl m Z ddl m Z m Z mZmZddlmZddlmZmZdd lmZmZdd lmZmZesQd gZercdd dZerbeesbdd gZndd gZGdddeZdS))Sequence)AnyClassVarOptionalUnionN)Tensor)Literal)_LPIPS_lpips_compute _lpips_update _NoTrainLpips)Metric)_SKIP_SLOW_DOCTEST_try_proceed_with_timeout)_MATPLOTLIB_AVAILABLE_TORCHVISION_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE*LearnedPerceptualImagePatchSimilarity.plotreturncCstddddS)NTvgg) pretrainednet)r rrT/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/image/lpip.py_download_lpips sr%LearnedPerceptualImagePatchSimilarityc seZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e ed <e ed <d Z eed<d gZeeeed<   d&deddeddededdf fdd Zde de ddfddZde fd d!Z d'd"eee ee fd#eedefd$d%ZZS)(rad The Learned Perceptual Image Patch Similarity (`LPIPS_`) calculates perceptual similarity between two images. LPIPS essentially computes the similarity between the activations of two image patches for some pre-defined network. This measure has been shown to match human perception well. A low LPIPS score means that image patches are perceptual similar. Both input image patches are expected to have shape ``(N, 3, H, W)``. The minimum size of `H, W` depends on the chosen backbone (see `net_type` arg). .. hint:: Using this metrics 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 - ``img1`` (:class:`~torch.Tensor`): tensor with images of shape ``(N, 3, H, W)`` - ``img2`` (:class:`~torch.Tensor`): tensor with images of shape ``(N, 3, H, W)`` As output of `forward` and `compute` the metric returns the following output - ``lpips`` (:class:`~torch.Tensor`): returns float scalar tensor with average LPIPS value over samples Args: net_type: str indicating backbone network type to use. Choose between `'alex'`, `'vgg'` or `'squeeze'` reduction: str indicating how to reduce over the batch dimension. Choose between `'sum'` or `'mean'`. normalize: by default this is ``False`` meaning that the input is expected to be in the [-1,1] range. If set to ``True`` will instead expect input to be in the ``[0,1]`` range. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ModuleNotFoundError: If ``torchvision`` package is not installed ValueError: If ``net_type`` is not one of ``"vgg"``, ``"alex"`` or ``"squeeze"`` ValueError: If ``reduction`` is not one of ``"mean"`` or ``"sum"`` Example: >>> from torch import rand >>> from torchmetrics.image.lpip import LearnedPerceptualImagePatchSimilarity >>> lpips = LearnedPerceptualImagePatchSimilarity(net_type='squeeze') >>> # LPIPS needs the images to be in the [-1, 1] range. >>> img1 = (rand(10, 3, 100, 100) * 2) - 1 >>> img2 = (rand(10, 3, 100, 100) * 2) - 1 >>> lpips(img1, img2) tensor(0.1024) Tis_differentiableFhigher_is_betterfull_state_updateplot_lower_boundg?plot_upper_bound sum_scorestotalrfeature_network__jit_ignored_attributes__alexmeannet_typerr'squeeze reduction)sumr( normalizekwargsrNc stjdi|tstdd}||vr td|d|dt|d|_d}||vr6td|d|||_t|t sEtd |||_ |j d t d d d |j dt d d d dS)NzLPIPS metric requires that torchvision is installed. Either install as `pip install torchmetrics[image]` or `pip install torchvision`.r*z#Argument `net_type` must be one of z , but got .)r)r(r-z$Argument `reduction` must be one of z/Argument `normalize` should be an bool but got r#r r-)dist_reduce_fxr$r)super__init__rModuleNotFoundError ValueErrorr rr, isinstanceboolr. add_statetorchtensor)selfr)r,r.r/valid_net_typevalid_reduction __class__rrr3hs$  z.LearnedPerceptualImagePatchSimilarity.__init__img1img2cCs<t|||j|jd\}}|j|7_|j|7_dS)z(Update internal states with lpips score.)rr.N)r rr.r#r-r$)r;r@rAlossr$rrrupdatesz,LearnedPerceptualImagePatchSimilarity.updatecCst|j|j|jS)z+Compute final perceptual similarity metric.)r r#r$r,)r;rrrcomputesz-LearnedPerceptualImagePatchSimilarity.computevalaxcCs |||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.lpip import LearnedPerceptualImagePatchSimilarity >>> metric = LearnedPerceptualImagePatchSimilarity(net_type='squeeze') >>> metric.update(torch.rand(10, 3, 100, 100), torch.rand(10, 3, 100, 100)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.image.lpip import LearnedPerceptualImagePatchSimilarity >>> metric = LearnedPerceptualImagePatchSimilarity(net_type='squeeze') >>> values = [ ] >>> for _ in range(3): ... values.append(metric(torch.rand(10, 3, 100, 100), torch.rand(10, 3, 100, 100))) >>> fig_, ax_ = metric.plot(values) )_plot)r;rErFrrrplots (r)r'r(F)NN)__name__ __module__ __qualname____doc__rr7__annotations__rrr!floatr"rr%strr&rlistrrr3rCrDrrrrrrH __classcell__rrr>rr)sF  1      )rN)collections.abcrtypingrrrrr9rtyping_extensionsr#torchmetrics.functional.image.lpipsr r r r torchmetrics.metricr torchmetrics.utilities.checksrrtorchmetrics.utilities.importsrrtorchmetrics.utilities.plotrr__doctest_skip__rrrrrrs&