o yi5@shddlmZddlZddlmZddlmZddlmZmZddl m Z ddl m Z Gdd d e Z dS) )AnyN)Tensor)Literal) _kld_compute _kld_update)Metric) dim_zero_catc seZdZUdZdZeed<dZeed<dZeed<e ed<  dd ed e d d e d dffdd Z de de d dfddZ d e fddZZS) KLDivergenceaComputes 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: >>> import torch >>> from torchmetrics.functional import kl_divergence >>> p = torch.tensor([[0.36, 0.48, 0.16]]) >>> q = torch.tensor([[1/3, 1/3, 1/3]]) >>> kl_divergence(p, q) tensor(0.0853) Tis_differentiableFhigher_is_betterfull_state_updatetotalmeanlog_prob reductionrsumnoneNkwargsreturnNc stjd i|t|tstd|||_gd}||vr*td|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 )rrmeasuresgr)dist_reduce_fxcatr r) super__init__ isinstancebool TypeErrorr ValueErrorr add_statetorchtensor)selfrrrallowed_reduction __class__rY/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/regression/kl_divergence.pyrNs  zKLDivergence.__init__pqcCsZt|||j\}}|jdus|jdkr|j|dS|j|7_|j|7_dSNr)rrrrappendrr )r#r(r)rr rrr'updateds zKLDivergence.updatecCs4|jdus |jdkrt|jn|j}t||j|jSr*)rrrrr )r#rrrr'computels$zKLDivergence.compute)Fr)__name__ __module__ __qualname____doc__r r__annotations__r r rrrrr,r- __classcell__rrr%r'r s&  /  r )typingrr!rtyping_extensionsr0torchmetrics.functional.regression.kl_divergencerrtorchmetrics.metricrtorchmetrics.utilities.datarr rrrr's