o yi}@sddlmZmZmZmZddlZddlmZddlmZddl m Z ddl m Z ddl mZddlmZdd lmZd d giZGd d d e ZdS))AnyListTupleUnionN)Tensor)Module)NoTrainInceptionV3)Metric)rank_zero_warn) dim_zero_cat)_TORCH_FIDELITY_AVAILABLE)InceptionScoreIStorch_fidelityc seZdZUdZdZeed<dZeed<dZeed<e ed<  dd e e e e fd e d ed eddf fdd ZdeddfddZdeeeffddZZS)r a` Calculate the Inception Score (IS) which is used to access how realistic generated images are. .. math:: IS = exp(\mathbb{E}_x KL(p(y | x ) || p(y))) where :math:`KL(p(y | x) || p(y))` is the KL divergence between the conditional distribution :math:`p(y|x)` and the margianl distribution :math:`p(y)`. Both the conditional and marginal distribution is calculated from features extracted from the images. The score is calculated on random splits of the images such that both a mean and standard deviation of the score are returned. The metric was originally proposed in `inception ref1`_. Using the default feature extraction (Inception v3 using the original weights from `inception ref2`_), the input is expected to be mini-batches of 3-channel RGB images of shape ``(3 x H x W)``. If argument ``normalize`` is ``True`` images are expected to be dtype ``float`` and have values in the ``[0, 1]`` range, else if ``normalize`` is set to ``False`` images are expected to have dtype uint8 and take values in the ``[0, 255]`` range. All images will be resized to 299 x 299 which is the size of the original training data. .. note:: using this metric with the default feature extractor requires that ``torch-fidelity`` is installed. Either install as ``pip install torchmetrics[image]`` or ``pip install torch-fidelity`` As input to ``forward`` and ``update`` the metric accepts the following input - ``imgs`` (:class:`~torch.Tensor`): tensor with images feed to the feature extractor As output of `forward` and `compute` the metric returns the following output - ``fid`` (:class:`~torch.Tensor`): float scalar tensor with mean FID value over samples Args: feature: Either an str, integer or ``nn.Module``: - an str or integer will indicate the inceptionv3 feature layer to choose. Can be one of the following: 'logits_unbiased', 64, 192, 768, 2048 - an ``nn.Module`` for using a custom feature extractor. Expects that its forward method returns an ``(N,d)`` matrix where ``N`` is the batch size and ``d`` is the feature size. splits: integer determining how many splits the inception score calculation should be split among kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ValueError: If ``feature`` is set to an ``str`` or ``int`` and ``torch-fidelity`` is not installed ValueError: If ``feature`` is set to an ``str`` or ``int`` and not one of ``('logits_unbiased', 64, 192, 768, 2048)`` TypeError: If ``feature`` is not an ``str``, ``int`` or ``torch.nn.Module`` Example: >>> import torch >>> _ = torch.manual_seed(123) >>> from torchmetrics.image.inception import InceptionScore >>> inception = InceptionScore() >>> # generate some images >>> imgs = torch.randint(0, 255, (100, 3, 299, 299), dtype=torch.uint8) >>> inception.update(imgs) >>> inception.compute() (tensor(1.0544), tensor(0.0117)) Fis_differentiableThigher_is_betterfull_state_updatefeatureslogits_unbiased featuresplits normalizekwargsreturnNc stjd i|tdtt|ttfr7tstdd}||vr,t d|d|dt dt|gd|_ n t|t r@||_ nt d t|tsMt d ||_||_|jd gdd dS)NzMetric `InceptionScore` will save all extracted features in buffer. For large datasets this may lead to large memory footprint.zInceptionScore metric requires that `Torch-fidelity` is installed. Either install as `pip install torchmetrics[image]` or `pip install torch-fidelity`.)r@iiz3Integer input to argument `feature` must be one of z , but got .zinception-v3-compat)name features_listz'Got unknown input to argument `feature`z*Argument `normalize` expected to be a boolr)dist_reduce_fx)super__init__r UserWarning isinstancestrintr ModuleNotFoundError ValueErrorr inceptionr TypeErrorboolrr add_state)selfrrrrvalid_int_input __class__r!P/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/image/inception.pyr#`s0  zInceptionScore.__init__imgscCs0|jr |dn|}||}|j|dS)z)Update the state with extracted features.N)rbyter*rappend)r.r3rr!r!r2updates zInceptionScore.updatecCst|j}t|jd}||}|jdd}|jdd}|j|jdd}|j|jdd}dd|D}ddt |||D}dd|D}t |}| | fS)NrdimcSsg|] }|jdddqS)rT)r:keepdim)mean).0pr!r!r2 sz*InceptionScore.compute..cSs"g|] \}}}|||qSr!)log)r=r>log_pm_pr!r!r2r?s"cSs g|] }|jddqS)r8r9)sumr<exp)r=kr!r!r2r?s ) r rtorchrandpermshapesoftmax log_softmaxchunkrzipstackr<std)r.ridxproblog_prob mean_probkl_klr!r!r2computes    zInceptionScore.compute)rrF)__name__ __module__ __qualname____doc__rr,__annotations__rrrrr&r'rrr#rr7rrU __classcell__r!r!r0r2r s,  <   (r )typingrrrrrFrtorch.nnrtorchmetrics.image.fidrtorchmetrics.metricr torchmetrics.utilitiesr torchmetrics.utilities.datar torchmetrics.utilities.importsr __doctest_requires__r r!r!r!r2s