o .wi @sddlmZddlZddlmZddlmZddlmZddlm Z deded e d e ee ffd d Z ddedee efdedd efddZ ddeded e dedd ef ddZdS))UnionN)Tensor)Literal) kl_divergence)_check_same_shapepqlog_probreturncCst|||jdks|jdkrtd|jd|jd|jd}|rOtjt||gddttd}dt |||d d dt |||d d }||fS||j d d d }||j d d d }||d}dt |||d d dt |||d d }||fS)aUpdate and returns jensen-shannon divergence scores for each observation and the total number of observations. Args: p: data distribution with shape ``[N, d]`` q: prior or approximate distribution with shape ``[N, d]`` 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 z4Expected both p and q distribution to be 2D but got z and z respectivelyr)dimg@g?N)r reductionT)axiskeepdim) rndim ValueErrorshapetorch logsumexpstacklogtensorrsum)rrr totalmeanmeasuresrm/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/functional/regression/js_divergence.py _jsd_updates"  (    rrrrr )rrnoneNcCs@|dkr|S|dkr||S|dus|dkr|S||S)zPCompute and reduce the Jensen-Shannon divergence based on the type of reduction.rrNr )r)rrr rrr _jsd_compute7s r!FcCst|||\}}t|||S)a*Compute `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)`. Args: p: data distribution with shape ``[N, d]`` q: prior or approximate distribution with shape ``[N, d]`` 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 Example: >>> from torch import tensor >>> p = tensor([[0.36, 0.48, 0.16]]) >>> q = tensor([[1/3, 1/3, 1/3]]) >>> jensen_shannon_divergence(p, q) tensor(0.0225) )rr!)rrr r rrrrrjensen_shannon_divergenceDs! r")r)Fr)typingrrrtyping_extensionsr0torchmetrics.functional.regression.kl_divergencertorchmetrics.utilities.checksrbooltupleintrr!r"rrrrs:     "