o ,h"@sddlmZmZddlZddlmZddlmZddlmZddl m Z ddl m Z m Z ddlmZdd lmZd gZGd d d eZdS) )OptionalUnionN)Tensor) constraints) Distribution) Independent)ComposeTransform Transform)_sum_rightmost)_sizeTransformedDistributionc seZdZUdZiZeeejfe d< dde de e e e fdeeddffdd Zdfd d Zejd d ddZedefddZefddZefdedefddZddZddZddZddZZ S) r a Extension of the Distribution class, which applies a sequence of Transforms to a base distribution. Let f be the composition of transforms applied:: X ~ BaseDistribution Y = f(X) ~ TransformedDistribution(BaseDistribution, f) log p(Y) = log p(X) + log |det (dX/dY)| Note that the ``.event_shape`` of a :class:`TransformedDistribution` is the maximum shape of its base distribution and its transforms, since transforms can introduce correlations among events. An example for the usage of :class:`TransformedDistribution` would be:: # Building a Logistic Distribution # X ~ Uniform(0, 1) # f = a + b * logit(X) # Y ~ f(X) ~ Logistic(a, b) base_distribution = Uniform(0, 1) transforms = [SigmoidTransform().inv, AffineTransform(loc=a, scale=b)] logistic = TransformedDistribution(base_distribution, transforms) For more examples, please look at the implementations of :class:`~torch.distributions.gumbel.Gumbel`, :class:`~torch.distributions.half_cauchy.HalfCauchy`, :class:`~torch.distributions.half_normal.HalfNormal`, :class:`~torch.distributions.log_normal.LogNormal`, :class:`~torch.distributions.pareto.Pareto`, :class:`~torch.distributions.weibull.Weibull`, :class:`~torch.distributions.relaxed_bernoulli.RelaxedBernoulli` and :class:`~torch.distributions.relaxed_categorical.RelaxedOneHotCategorical` arg_constraintsNbase_distribution transforms validate_argsreturncsbt|tr |g|_nt|tr tdd|Dstd||_ntd||j|j}t|j}t |j}t||j j krLtd|j j d|d| |}| |}||kri|dt||} || }|j j |} | dkrxt|| }||_|jj |j j } t|jj || } t|| ksJt|| } |d| }|| d}tj|||d dS) Ncss|]}t|tVqdSN) isinstancer ).0trg/var/www/html/scripts/venv/lib/python3.10/site-packages/torch/distributions/transformed_distribution.py @sz3TransformedDistribution.__init__..z6transforms must be a Transform or a list of Transformsz0transforms must be a Transform or list, but was z9base_distribution needs to have shape with size at least z , but got .rr)rr rlistall ValueError batch_shape event_shapelenrdomain event_dim forward_shape inverse_shapeexpandr base_distcodomainmaxsuper__init__)selfrrr base_shapebase_event_dim transformr#expanded_base_shapebase_batch_shapereinterpreted_batch_ndimstransform_change_in_event_dimr"cutrr __class__rrr*5sV            z TransformedDistribution.__init__cs|t|}t|}||j}t|jD]}||}q|dt|t|j j}|j ||_ |j|_t t|j ||jdd|j |_ |S)NFr)_get_checked_instancer torchSizerreversedrr$r r&r%r)r*_validate_args)r+r _instancenewshaperr0r4rrr%ns     zTransformedDistribution.expandF) is_discretecCsF|js|jjS|jdj}t|j|jkr!t|t|j|j}|S)N) rr&supportr'r rr"r independent)r+r@rrrr@}s zTransformedDistribution.supportcCs|jjSr)r& has_rsample)r+rrrrBsz#TransformedDistribution.has_rsamplecCsPt|j|}|jD]}||}q|WdS1s!wYdS)a Generates a sample_shape shaped sample or sample_shape shaped batch of samples if the distribution parameters are batched. Samples first from base distribution and applies `transform()` for every transform in the list. N)r7no_gradr&samplerr+ sample_shapexr.rrrrDs    $zTransformedDistribution.samplerFcCs$|j|}|jD]}||}q |S)a$ Generates a sample_shape shaped reparameterized sample or sample_shape shaped batch of reparameterized samples if the distribution parameters are batched. Samples first from base distribution and applies `transform()` for every transform in the list. )r&rsamplerrErrrrHs   zTransformedDistribution.rsamplecCs|jr||t|j}d}|}t|jD]"}||}||jj|j j7}|t | ||||jj}|}q|t |j ||t|j j}|S)z Scores the sample by inverting the transform(s) and computing the score using the score of the base distribution and the log abs det jacobian. g)r:_validate_sampler rr9rinvr!r"r'r log_abs_det_jacobianr&log_prob)r+valuer"rLyr.rGrrrrLs"     z TransformedDistribution.log_probcCs@d}|jD]}||j}qt|tr|dkr|S||ddS)zu This conditionally flips ``value -> 1-value`` to ensure :meth:`cdf` is monotone increasing. g?)rsignrint)r+rMrPr.rrr_monotonize_cdfs   z'TransformedDistribution._monotonize_cdfcCsL|jdddD]}||}q|jr|j||j|}||}|S)z Computes the cumulative distribution function by inverting the transform(s) and computing the score of the base distribution. Nr?)rrJr:r&rIcdfrRr+rMr.rrrrSs    zTransformedDistribution.cdfcCs.||}|j|}|jD]}||}q|S)z Computes the inverse cumulative distribution function using transform(s) and computing the score of the base distribution. )rRr&icdfrrTrrrrUs    zTransformedDistribution.icdfr)!__name__ __module__ __qualname____doc__r dictstrr Constraint__annotations__rrr rrboolr*r%dependent_propertyr@propertyrBr7r8rDr rrHrLrRrSrU __classcell__rrr4rr s0 !9       )typingrrr7rtorch.distributionsr torch.distributions.distributionrtorch.distributions.independentrtorch.distributions.transformsrr torch.distributions.utilsr torch.typesr __all__r rrrrs