:jddlmZddlmZmZmZmZmZddlZddlm Z ddl m Z ddl m Z mZddlmZddlmZdd lmZdd lmZmZesd gZGd d eZy))Sequence)AnyListOptionalUnioncastN)Tensor)Literal) _kld_compute _kld_update)Metric) dim_zero_cat)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzKLDivergence.plotc eZdZUdZdZeed<dZeed<dZeed<dZ e ed<e e e e fed <e ed < dd ed ed deddffd Zde de ddfdZde fdZ ddee e ee fdeedefdZxZS) KLDivergenceaCompute the `KL divergence`_. .. math:: D_{KL}(P||Q) = \sum_{x\in\mathcal{X}} P(x) \log\frac{P(x)}{Q{x}} Where :math:`P` and :math:`Q` are probability distributions where :math:`P` usually represents a distribution over data and :math:`Q` is often a prior or approximation of :math:`P`. It should be noted that the KL divergence is a non-symmetrical metric i.e. :math:`D_{KL}(P||Q) \neq D_{KL}(Q||P)`. As input to ``forward`` and ``update`` the metric accepts the following input: - ``p`` (:class:`~torch.Tensor`): a data distribution with shape ``(N, d)`` - ``q`` (:class:`~torch.Tensor`): prior or approximate distribution with shape ``(N, d)`` As output of ``forward`` and ``compute`` the metric returns the following output: - ``kl_divergence`` (:class:`~torch.Tensor`): A tensor with the KL divergence Args: log_prob: bool indicating if input is log-probabilities or probabilities. If given as probabilities, will normalize to make sure the distributes sum to 1. reduction: Determines how to reduce over the ``N``/batch dimension: - ``'mean'`` [default]: Averages score across samples - ``'sum'``: Sum score across samples - ``'none'`` or ``None``: Returns score per sample kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: TypeError: If ``log_prob`` is not an ``bool``. ValueError: If ``reduction`` is not one of ``'mean'``, ``'sum'``, ``'none'`` or ``None``. .. attention:: Half precision is only support on GPU for this metric. Example: >>> from torch import tensor >>> from torchmetrics.regression import KLDivergence >>> p = tensor([[0.36, 0.48, 0.16]]) >>> q = tensor([[1/3, 1/3, 1/3]]) >>> kl_divergence = KLDivergence() >>> kl_divergence(p, q) tensor(0.0853) Tis_differentiableFhigher_is_betterfull_state_updateplot_lower_boundmeasurestotallog_prob reductionmeansumnoneNkwargsreturnNc t|d i|t|tst d|||_gd}||vrt d|d|||_|jdvr(|jdtjdd n|jdgd |jd tjd d y)Nz0Expected argument `log_prob` to be bool but got rz+Expected argument `reduction` to be one of z but got )rrrrr)dist_reduce_fxcatrr) super__init__ isinstancebool TypeErrorr ValueErrorr add_statetorchtensor)selfrrr!allowed_reduction __class__s z/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchmetrics/regression/kl_divergence.pyr(zKLDivergence.__init__\s "6"(D)NxjYZ Z  9 - -JK\J]]fgpfqrs s" >>_ , NN:u||C'8N O NN:r%N @ w QFpqcZt|||j\}}|j|jdk(r1ttt |j j|ytt |j |jz|_|xj|z c_ y)z2Update metric states with predictions and targets.Nr ) r rrrrr rappendrr)r0r5r6rrs r3updatezKLDivergence.updatersu%aDMM:% >> !T^^v%= ft}} - 4 4X > 7(,,.HDM JJ% Jr4c|jdvr*tttt|j ntt|j }t ||j|jS)zCompute metric.)r N)rrrrr rr r)r0rs r3computezKLDivergence.compute{sU~~/ d6lDMM: ;fdmm,  Hdjj$..AAr4valaxc&|j||S)aCPlot 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 >>> from torch import randn >>> # Example plotting a single value >>> from torchmetrics.regression import KLDivergence >>> metric = KLDivergence() >>> metric.update(randn(10,3).softmax(dim=-1), randn(10,3).softmax(dim=-1)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> from torch import randn >>> # Example plotting multiple values >>> from torchmetrics.regression import KLDivergence >>> metric = KLDivergence() >>> values = [] >>> for _ in range(10): ... values.append(metric(randn(10,3).softmax(dim=-1), randn(10,3).softmax(dim=-1))) >>> fig, ax = metric.plot(values) )_plot)r0r<r=s r3plotzKLDivergence.plotsPzz#r""r4)Fr)NN)__name__ __module__ __qualname____doc__rr*__annotations__rrrfloatrr rr rr(r9r;rrrrr@ __classcell__)r2s@r3rrs0d#t""d"#t#!e!FDL()) M :@GG67G G  G,  6 d BB_c(#E&(6*:":;<(#IQRZI[(# (#r4r)collections.abcrtypingrrrrrr.r typing_extensionsr 0torchmetrics.functional.regression.kl_divergencer r torchmetrics.metricr torchmetrics.utilities.datartorchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rr&r4r3rQsB%33 %V&4@@+,M#6M#r4