a  d.@sddlmZmZddlZddlmZddlmZddlmZddl m Z eee eee fddd Z deee efed ed d dZdeee ed edddZdS))TupleUnionN)Tensor)Literal)_check_same_shape) _safe_xlogy)pqlog_probreturncCst|||jdks|jdkr8td|jd|jd|jd}|rbtj|||dd}n:||jddd }||jddd }t|||jdd}||fS) aUpdate and returns KL 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)axisT)rZkeepdim)rndim ValueErrorshapetorchsumexpr)rr r totalmeasuresry/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/functional/regression/kl_divergence.py _kld_updates  rmean)rrnoneN)rr reductionr cCs@|dkr|S|dkr$||S|dus4|dkr8|S||S)aCompute 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 rF)rr r rr cCst|||\}}t|||S)aCompute `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: >>> from torch import tensor >>> p = tensor([[0.36, 0.48, 0.16]]) >>> q = tensor([[1/3, 1/3, 1/3]]) >>> kl_divergence(p, q) tensor(0.0853) )rr)rr r rrrrrr kl_divergenceRs r)r)Fr)typingrrrrZtyping_extensionsrZtorchmetrics.utilities.checksrZtorchmetrics.utilities.computerboolintrrrrrrrs      !