o .wiw@sddlmZddlmZmZmZmZmZmZddl Z ddl m Z ddl m Z ddl mZmZddlmZddlmZdd lmZdd lmZmZesMd gZGd d d eZdS))log)AnyListOptionalSequenceUnioncastN)Tensor)Literal) _jsd_compute _jsd_update)Metric) dim_zero_cat)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEJensenShannonDivergence.plotc seZdZUdZdZeed<dZeed<dZeed<dZ e ed<e d Z e ed <e eeefed <eed <  d dededdeddffdd ZdededdfddZdefddZ d!dee eeefdeedefddZZS)"JensenShannonDivergenceaaCompute the `Jensen-Shannon divergence`_. .. math:: D_{JS}(P||Q) = \frac{1}{2} D_{KL}(P||M) + \frac{1}{2} D_{KL}(Q||M) 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`. :math:`D_{KL}` is the `KL divergence`_ and :math:`M` is the average of the two distributions. It should be noted that the Jensen-Shannon divergence is a symmetrical metric i.e. :math:`D_{JS}(P||Q) = D_{JS}(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: - ``js_divergence`` (:class:`~torch.Tensor`): A tensor with the Jensen-Shannon 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 JensenShannonDivergence >>> p = tensor([[0.1, 0.9], [0.2, 0.8], [0.3, 0.7]]) >>> q = tensor([[0.3, 0.7], [0.4, 0.6], [0.5, 0.5]]) >>> js_div = JensenShannonDivergence() >>> js_div(p, q) tensor(0.0259) Tis_differentiableFhigher_is_betterfull_state_updateplot_lower_boundplot_upper_boundmeasurestotalmeanlog_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 r z+Expected argument `reduction` to be one of z but got )rr!rrr!)dist_reduce_fxcatrr) super__init__ isinstancebool TypeErrorr ValueErrorr add_statetorchtensor)selfrrr#allowed_reduction __class__r'b/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/regression/js_divergence.pyr)\s  z JensenShannonDivergence.__init__pqcCsht|||j\}}|jdus|jdkr ttt|j|dStt|j||_|j |7_ dS)zUpdate the metric state.Nr") r rrrrr rappendr!r)r1r6r7rrr'r'r5updaters zJensenShannonDivergence.updatecCs:|jdvrtttt|jntt|j}t||j|jS)zCompute metric.)r"N)rrrrr rr r)r1rr'r'r5compute{s  zJensenShannonDivergence.computevalaxcCs |||S)aoPlot 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 JensenShannonDivergence >>> metric = JensenShannonDivergence() >>> 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 JensenShannonDivergence >>> metric = JensenShannonDivergence() >>> 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)r1r;r<r'r'r5plots (r)Fr)NN)__name__ __module__ __qualname____doc__rr+__annotations__rrrfloatrrrr rr rr)r9r:rrrrr> __classcell__r'r'r3r5rs<  3     r)mathrtypingrrrrrrr/r typing_extensionsr 0torchmetrics.functional.regression.js_divergencer r torchmetrics.metricr torchmetrics.utilities.datartorchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rr'r'r'r5s