o yi @sddlmZddlZddlmZddlmZddlmZddlm Z deded e d eee ffd d Z ddedededd efddZ ddeded e dedd ef ddZdS))TupleN)Tensor)Literal)_check_same_shape) _safe_xlogypqlog_probreturncCst|||jdks|jdkrtd|jd|jd|jd}|r4tj|||dd}||fS||jddd }||jddd }t|||jdd}||fS) aUpdates and returns KL divergence scores for each observation and the total number of observations. Checks same shape and 2D nature of the input tensors else raises ValueError. 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)axisT)r keepdim)rndim ValueErrorshapetorchsumexpr)rrr totalmeasuresrd/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/functional/regression/kl_divergence.py _kld_updates  rmeanrr reduction)rrnoneNcCs@|dkr|S|dkr||S|dus|dkr|S||S)aComputes the KL divergenece based on the type of reduction. Args: measures: Tensor of KL divergence scores for each observation total: Number of observations 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: >>> p = torch.tensor([[0.36, 0.48, 0.16]]) >>> q = torch.tensor([[1/3, 1/3, 1/3]]) >>> measures, total = _kld_update(p, q, log_prob=False) >>> _kld_compute(measures, total) tensor(0.0853) rrNr)r)rrrrrr _kld_compute2s rFcCst|||\}}t|||S)aComputes `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)`. 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: >>> import torch >>> 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) )rr)rrr rrrrrr kl_divergencePs r)r)Fr)typingrrrtyping_extensionsrtorchmetrics.utilities.checksrtorchmetrics.utilities.computerboolintrrrrrrrs(     "