9iSSKJrJr SSKrSSKJr SSKJr SSKJr SSK J r SSK J r SSK JrJr S /r"S S \ 5rg) )OptionalUnionN)Tensor) constraints) Dirichlet)ExponentialFamily) broadcast_all)_Number_sizeBetac ^\rSrSrSr\R \R S.r\Rr Sr SS\ \ \ 4S\ \ \ 4S\\S S4U4S jjjrSU4S jjr\S \ 4S j5r\S \ 4S j5r\S \ 4Sj5rSS\S \ 4SjjrSrSr\S \ 4Sj5r\S \ 4Sj5r\S \\ \ 44Sj5rSrSrU=r $)r aB Beta distribution parameterized by :attr:`concentration1` and :attr:`concentration0`. Example:: >>> # xdoctest: +IGNORE_WANT("non-deterministic") >>> m = Beta(torch.tensor([0.5]), torch.tensor([0.5])) >>> m.sample() # Beta distributed with concentration concentration1 and concentration0 tensor([ 0.1046]) Args: concentration1 (float or Tensor): 1st concentration parameter of the distribution (often referred to as alpha) concentration0 (float or Tensor): 2nd concentration parameter of the distribution (often referred to as beta) concentration1concentration0TNrr validate_argsreturncZ>[U[5(a@[U[5(a+[R"[ U5[ U5/5nO%[ X5up[R "X/S5n[XCS9Ul[TU])URRUS9 g)Nr) isinstancer torchtensorfloatr stackr _dirichletsuper__init__ _batch_shape)selfrrrconcentration1_concentration0 __class__s X/var/www/html/land-doc-ocr/venv/lib/python3.13/site-packages/torch/distributions/beta.pyr Beta.__init__)s ng . .:ng3V3V,1LL~&n(=>- ).;. *N-2KK0"- )$ )  55]Sc>UR[U5n[R"U5nURR U5Ul[ [U]USS9 URUlU$)NFr) _get_checked_instancer rSizerexpandrr_validate_args)r batch_shape _instancenewr"s r#r) Beta.expand?s`((y9jj- // < dC!+U!C!00 r%cNURURUR-- $Nrr s r#mean Beta.meanGs$""d&9&9Drvs7" +3<3& (eG eGr%