a h"@sddlmZmZddlZddlmZddlmZddlmZddl m Z ddl m Z m Z ddlmZdd lmZd gZGd d d eZdS) )OptionalUnionN)Tensor) constraints) Distribution) Independent)ComposeTransform Transform)_sum_rightmost)_sizeTransformedDistributioncseZdZUdZiZeeejfe d<de e e e e feeddfdd Zdfdd Zejd d d d Zeed ddZefddZefeedddZddZddZddZddZZ 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_constraintsN)base_distribution transforms validate_argsreturncsdt|tr|g|_n:t|tr@tdd|Ds8td||_ntd||j|j}t|j}t |j}t||j j krtd|j j d|d| |}| |}||kr|dt||} || }|j j |} | dkrt|| }||_|jj |j j } t|jj || } t|| ks*Jt|| } |d| }|| d}tj|||d dS) Ncss|]}t|tVqdSN) isinstancer ).0trZ/var/www/auris/lib/python3.9/site-packages/torch/distributions/transformed_distribution.py @z3TransformedDistribution.__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__)selfrrrZ base_shapeZbase_event_dim transformr$Zexpanded_base_shapebase_batch_shapeZreinterpreted_batch_ndimsZtransform_change_in_event_dimr#Zcutrr  __class__rrr+5sV            z TransformedDistribution.__init__cs|t|}t|}||j}t|jD]}||}q*|dt|t|j j}|j ||_ |j|_t t|j ||jdd|j |_ |S)NFr)Z_get_checked_instancer torchSizer reversedrr%r!r'r&r*r+_validate_args)r,rZ _instancenewshaperr.r/rrr&ns     zTransformedDistribution.expandF)Z is_discretecCsF|js|jjS|jdj}t|j|jkrBt|t|j|j}|S)N) rr'supportr(r!r r#rZ independent)r,r8rrrr8}s zTransformedDistribution.support)rcCs|jjSr)r' has_rsample)r,rrrr9sz#TransformedDistribution.has_rsamplecCsPt4|j|}|jD] }||}q|WdS1sB0YdS)a Generates a sample_shape shaped sample or sample_shape shaped batch of samples if the distribution parameters are batched. Samples first from base distribution and applies `transform()` for every transform in the list. N)r1Zno_gradr'samplerr, sample_shapexr-rrrr:s     zTransformedDistribution.sample)r<rcCs$|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'rsamplerr;rrrr>s   zTransformedDistribution.rsamplecCs|jr||t|j}d}|}t|jD]D}||}||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)r4_validate_sampler!r r3rinvr"r#r(r Zlog_abs_det_jacobianr'log_prob)r,valuer#rAyr-r=rrrrAs"     z TransformedDistribution.log_probcCs@d}|jD]}||j}q t|tr0|dkr0|S||ddS)zu This conditionally flips ``value -> 1-value`` to ensure :meth:`cdf` is monotone increasing. g?)rsignrint)r,rBrEr-rrr_monotonize_cdfs   z'TransformedDistribution._monotonize_cdfcCsL|jdddD]}||}q|jr2|j||j|}||}|S)z Computes the cumulative distribution function by inverting the transform(s) and computing the score of the base distribution. Nr7)rr@r4r'r?cdfrGr,rBr-rrrrHs    zTransformedDistribution.cdfcCs.||}|j|}|jD] }||}q|S)z Computes the inverse cumulative distribution function using transform(s) and computing the score of the base distribution. )rGr'icdfrrIrrrrJs     zTransformedDistribution.icdf)N)N)!__name__ __module__ __qualname____doc__r dictstrr Constraint__annotations__rrr rrboolr+r&Zdependent_propertyr8propertyr9r1r2r:r rr>rArGrHrJ __classcell__rrr/rr s( !9      )typingrrr1rZtorch.distributionsrZ torch.distributions.distributionrZtorch.distributions.independentrZtorch.distributions.transformsrr Ztorch.distributions.utilsr Z torch.typesr __all__r rrrrs