a  d@sddlmZmZmZmZddlZddlmZddlmZddl m Z m Z ddl m Z ddlmZddlmZdd lmZmZesd gZGd d d e ZdS) )AnyOptionalSequenceUnionN)Tensor)Literal) _kld_compute _kld_update)Metric) dim_zero_cat)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEKLDivergence.plotcseZdZUdZdZeed<dZeed<dZeed<dZ e ed<e ed <dee d e d d fdd Ze e d dddZe dddZdeee ee feeedddZZS) 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-symetrical 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``. .. note:: 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_boundtotalmeanrsumnoneNN)log_prob reductionkwargsreturnc stjfi|t|ts*td|||_gd}||vrTtd|d|||_|jdvr||jdt ddd n|jdgd d |jd t d dd dS) Nz0Expected argument `log_prob` to be bool but got rz+Expected argument `reduction` to be one of z but got )rrmeasuresrr)Zdist_reduce_fxcatrr) super__init__ isinstancebool TypeErrorr ValueErrorrZ add_statetorchZtensor)selfrrrZallowed_reduction __class__n/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/regression/kl_divergence.pyr"Ys  zKLDivergence.__init__)pqrcCsXt|||j\}}|jdus&|jdkr4|j|n |j|7_|j|7_dS)z2Update metric states with predictions and targets.Nr)r rrrappendrr)r(r-r.rrr+r+r,updateos zKLDivergence.update)rcCs*|jdvrt|jn|j}t||j|jS)zCompute metric.)rN)rr rrr)r(rr+r+r,computexs  zKLDivergence.compute)valaxrcCs |||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) )Z_plot)r(r2r3r+r+r,plots(r)Fr)NN)__name__ __module__ __qualname____doc__rr$__annotations__rrrfloatrrrr"r0r1rrrr rr4 __classcell__r+r+r)r,rs* 1      r)typingrrrrr'rZtyping_extensionsrZ0torchmetrics.functional.regression.kl_divergencerr Ztorchmetrics.metricr Ztorchmetrics.utilities.datar Ztorchmetrics.utilities.importsr Ztorchmetrics.utilities.plotr rZ__doctest_skip__rr+r+r+r,s