o "j@sXddlZddlmZddlmZddlmZddlmZGdddej Z d dd Z dS) N)check_variable_and_dtype) LayerHelper)exponential_family)in_dynamic_modecsneZdZdZfddZeddZeddZdd d Zd d Z d dZ ddZ eddZ ddZ ZS) Dirichletab Dirichlet distribution with parameter "concentration". The Dirichlet distribution is defined over the `(k-1)-simplex` using a positive, lenght-k vector concentration(`k > 1`). The Dirichlet is identically the Beta distribution when `k = 2`. For independent and identically distributed continuous random variable :math:`\boldsymbol X \in R_k` , and support :math:`\boldsymbol X \in (0,1), ||\boldsymbol X|| = 1` , The probability density function (pdf) is .. math:: f(\boldsymbol X; \boldsymbol \alpha) = \frac{1}{B(\boldsymbol \alpha)} \prod_{i=1}^{k}x_i^{\alpha_i-1} where :math:`\boldsymbol \alpha = {\alpha_1,...,\alpha_k}, k \ge 2` is parameter, the normalizing constant is the multivariate beta function. .. math:: B(\boldsymbol \alpha) = \frac{\prod_{i=1}^{k} \Gamma(\alpha_i)}{\Gamma(\alpha_0)} :math:`\alpha_0=\sum_{i=1}^{k} \alpha_i` is the sum of parameters, :math:`\Gamma(\alpha)` is gamma function. Args: concentration (Tensor): "Concentration" parameter of dirichlet distribution, also called :math:`\alpha`. When it's over one dimension, the last axis denotes the parameter of distribution, ``event_shape=concentration.shape[-1:]`` , axes other than last are condsider batch dimensions with ``batch_shape=concentration.shape[:-1]`` . Examples: .. code-block:: python >>> import paddle >>> dirichlet = paddle.distribution.Dirichlet(paddle.to_tensor([1., 2., 3.])) >>> print(dirichlet.entropy()) Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True, -1.24434423) >>> print(dirichlet.prob(paddle.to_tensor([.3, .5, .6]))) Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True, 10.80000019) cs@|dkr td||_t|jdd|jdddS)Nz:`concentration` parameter must be at least one dimensional)dim ValueError concentrationsuper__init__shape)selfr  __class__^/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/paddle/distribution/dirichlet.pyr Gs &zDirichlet.__init__cCs|j|jjdddS)zbMean of Dirichelt distribution. Returns: Mean value of distribution. rTZkeepdim)r sumrrrrmeanPszDirichlet.meancCs2|jjddd}|j||j|d|dS)zjVariance of Dirichlet distribution. Returns: Variance value of distribution. rTrr)r rpow)rconcentration0rrrvarianceYszDirichlet.variancercCs,t|tr|nt|}t|j||S)zSample from dirichlet distribution. Args: shape (Sequence[int], optional): Sample shape. Defaults to empty tuple. ) isinstancetuple _dirichletr expandZ _extend_shape)rrrrrsampleeszDirichlet.samplecCst||S)zProbability density function(PDF) evaluated at value. Args: value (Tensor): Value to be evaluated. Returns: PDF evaluated at value. )paddleexplog_probrvaluerrrprobns zDirichlet.probcCs>t||jddt|jdt|jdS)zpLog of probability densitiy function. Args: value (Tensor): Value to be evaluated. ?r)r!logr rlgammar$rrrr#ys zDirichlet.log_probcCsb|jd}|jjd}t|jdt|||t||jdt|jdS)zbEntropy of Dirichlet distribution. Returns: Entropy of distribution. rr')r rrr!r)Zdigamma)rrkrrrentropys  zDirichlet.entropycCs|jfSN)r rrrr_natural_parametersszDirichlet._natural_parameterscCs|dt|dS)Nr)r)rr!)rxrrr_log_normalizerszDirichlet._log_normalizer)r)__name__ __module__ __qualname____doc__r propertyrrr r&r#r+r-r/ __classcell__rrrrrs 0       rcCsftr tj|Sd}t|dgd|t|fit}|j|jd}|j |d|id|iid|S)N dirichletr )Zfloat16Zfloat32Zfloat64Zuint16)dtypeAlphaZOut)typeZinputsZoutputsattrs) rr!Z_C_opsr6rrlocalsZ"create_variable_for_type_inferencer7Z append_op)r nameZop_typehelperoutrrrrs( rr,) r!Zpaddle.base.data_feederrZpaddle.base.layer_helperrZpaddle.distributionrZpaddle.frameworkrZExponentialFamilyrrrrrrs