DŽg!ddlmZddlZddlmZddlmZddlmZddl m Z m Z ddl m Z ddlmZd gZGd d eZy) )DictN) constraints) Distribution) Independent)ComposeTransform Transform)_sum_rightmost)_sizeTransformedDistributionc&eZdZUdZiZeeejfe d<dfd Z dfd Z ejddZ edZej"fd Zej"fd ed ej(fd Zd ZdZdZdZxZS)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_constraintsct|tr |g|_nCt|tr%t d|Ds t d||_nt d||j |jz}t|j}t|j}t||jjkr&t d|jjd|d|j|}|j|}||k7r"|dt||z } |j| }|jj|z } | dkDr t|| }||_|j"j|jjz } t%|j"j|| z} t|| k\sJt|| z } |d| }|| d}t&|Q|||y) Nc3<K|]}t|tywN) isinstancer).0ts t/home/mcse/projects/flask_80/flask-venv/lib/python3.12/site-packages/torch/distributions/transformed_distribution.py z3TransformedDistribution.__init__..9sDAz!Y/Dsz6transforms 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 .r validate_args)rr transformslistall ValueError batch_shape event_shapelenrdomain event_dim forward_shape inverse_shapeexpandr base_distcodomainmaxsuper__init__)selfbase_distributionrr base_shapebase_event_dim transformr"expanded_base_shapebase_batch_shapereinterpreted_batch_ndimstransform_change_in_event_dimr!cutrr __class__s rr)z TransformedDistribution.__init__3s j) ,DO D )DDD L)DOB:,O  '225F5R5RR .::;$T__5 z?Y--77 7KIL\L\LfLfKggqr|q}}~ "// ; '55mD , ,2;#)*^;  !2 8 89I J $-$4$4$>$>$O! $q ( +!#<! +    ( (9+;+;+E+E E &    ( ( : : =!Y...- 9,#DS) #CD)  kOc|jt|}tj|}||jz}t |j D]}|j|}|dt|t|jjz }|jj||_ |j |_tt|3||jd|j|_ |S)NFr)_get_checked_instancer torchSizerreversedrr#rr%r$r(r)_validate_args)r*r _instancenewshaperr0r4s rr$zTransformedDistribution.expandgs(()@)Ljj- d...$//* +AOOE*E + !O3u:DNN4N4N0O#OP--.>?  %s4 )) 5 "00 r5F) is_discretec,|js|jjS|jdj}t |j |j kDr6tj|t |j |j z }|S)N) rr%supportr&rrr!r independent)r*rBs rrBzTransformedDistribution.supportvsx>>)) )//"%.. t 7#4#4 4!--T--.1B1BBGr5c.|jjSr)r% has_rsample)r*s rrEz#TransformedDistribution.has_rsamples~~)))r5ctj5|jj|}|jD] }||} |cdddS#1swYyxYw)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)r8no_gradr%samplerr* sample_shapexr.s rrHzTransformedDistribution.samplesU]]_ %%l3A!__ ! aL !    s 6AArJreturncn|jj|}|jD] }||} |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%rsamplerrIs rrNzTransformedDistribution.rsamples9 NN " "< 0 I! A r5c(|jr|j|t|j}d}|}t |j D]{}|j |}||jj|jjz z }|t|j||||jjz z }|}}|t|jj||t|jjz z}|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_samplerrr:rinvr r!r&r log_abs_det_jacobianr%log_prob)r*valuer!rSyr.rKs rrSz TransformedDistribution.log_probs     ! !% ((()  !$//2 I a A ))33i6H6H6R6RR RI...q!4I,,666#HA n NN # #A & C8R8R4S(S  r5cd}|jD]}||jz}t|tr|dk(r|S||dz zdzS)zu This conditionally flips ``value -> 1-value`` to ensure :meth:`cdf` is monotone increasing. g?)rsignrint)r*rTrXr.s r_monotonize_cdfz'TransformedDistribution._monotonize_cdfsS  )I)..(D ) dC TQYLus{#c))r5c|jdddD]}|j|}|jr|jj ||jj |}|j |}|S)z Computes the cumulative distribution function by inverting the transform(s) and computing the score of the base distribution. NrA)rrQr;r%rPcdfrZr*rTr.s rr\zTransformedDistribution.cdfsr 2. )IMM%(E )    NN + +E 2""5)$$U+ r5c|j|}|jj|}|jD] }||} |S)z Computes the inverse cumulative distribution function using transform(s) and computing the score of the base distribution. )rZr%icdfrr]s rr_zTransformedDistribution.icdfsJ $$U+##E* %Ie$E % r5r)__name__ __module__ __qualname____doc__r rstrr Constraint__annotations__r)r$dependent_propertyrBpropertyrEr8r9rHr TensorrNrSrZr\r_ __classcell__)r4s@rr r s@:rts5 +97F4 % %HlHr5