o p i@srddlmZddlmZddlmZddlZddlmZm Z er&ddlm Z Gddde j Z d d Z d d ZdS) ) annotations)Iterable) TYPE_CHECKINGN) categorical distribution)TensorcseZdZUdZded<ded<dfdd Zedd d Zedd d ZdddZ dddZ gfdddZ dddZ d ddZ ZS)! Multinomiala$ Multinomial distribution parameterized by :attr:`total_count` and :attr:`probs`. In probability theory, the multinomial distribution is a generalization of the binomial distribution, it models the probability of counts for each side of a k-sided die rolled n times. When k is 2 and n is 1, the multinomial is the bernoulli distribution, when k is 2 and n is grater than 1, it is the binomial distribution, when k is grater than 2 and n is 1, it is the categorical distribution. The probability mass function (PMF) for multinomial is .. math:: f(x_1, ..., x_k; n, p_1,...,p_k) = \frac{n!}{x_1!...x_k!}p_1^{x_1}...p_k^{x_k} where, :math:`n` is number of trials, k is the number of categories, :math:`p_i` denote probability of a trial falling into each category, :math:`{\textstyle \sum_{i=1}^{k}p_i=1}, p_i \ge 0`, and :math:`x_i` denote count of each category. Args: total_count (int): Number of trials. probs (Tensor): Probability of a trial falling into each category. Last axis of probs indexes over categories, other axes index over batches. Probs value should between [0, 1], and sum to 1 along last axis. If the value over 1, it will be normalized to sum to 1 along the last axis. Examples: .. code-block:: python >>> import paddle >>> paddle.seed(2023) >>> multinomial = paddle.distribution.Multinomial(10, paddle.to_tensor([0.2, 0.3, 0.5])) >>> print(multinomial.sample((2, 3))) Tensor(shape=[2, 3, 3], dtype=float32, place=Place(cpu), stop_gradient=True, [[[1., 5., 4.], [0., 4., 6.], [1., 3., 6.]], [[2., 2., 6.], [0., 6., 4.], [3., 3., 4.]]]) int total_countrprobsreturnNonecst|tr |dkr td|dkrtd||jddd|_||_tj| |d|_ t |j dd|j dddS)NzBinput parameter total_count must be int type and grater than zero.z9probs parameter should not be none and over one dimensionT)Zkeepdim)logits) isinstancer ValueErrordimsumr r rZ Categorical_probs_to_logits _categoricalsuper__init__shape)selfr r  __class__f/home/app/PaddleOCR-VL/.venv_paddleocr/lib/python3.10/site-packages/paddle/distribution/multinomial.pyrMs &zMultinomial.__init__cCs |j|jS)z\mean of multinomial distribution. Returns: Tensor: mean value. )r r rrrrmean`s zMultinomial.meancCs|j|jd|jS)zdvariance of multinomial distribution. Returns: Tensor: variance value. r)r r rrrrvarianceiszMultinomial.variancevaluecCst||S)probability mass function evaluated at value. Args: value (Tensor): value to be evaluated. Returns: Tensor: probability of value. )paddleexplog_prob)rr"rrrprobrs zMultinomial.probcCst|r t||jj}tt|j|g\}}tr*d||dkt|@<ntj ||dkt|@d}t | ddt |d d|| dS)r#rrr) r$ is_integercastr dtypeZbroadcast_tensorslogZin_dynamic_modeisinfZstaticsetitemlgammar)rr"rrrrr&}s  zMultinomial.log_probr Iterable[int]cCsRt|ts td|j|jgt|}tjj ||j j d |j jdS)zdraw sample data from multinomial distribution Args: sample_shape (list|tuple, optional): [description]. Defaults to []. z%sample shape must be Iterable object.rr)rr TypeErrorrsampler listr$nnZ functionalZone_hotr rr)r*r)rrZsamplesrrrr1s  zMultinomial.samplecCstjg|j|jjd}tj|jd|jjdddt|jjdd}t | ||}||j t |d|t |dddgS) z`entropy of multinomial distribution Returns: Tensor: entropy value )rZ fill_valuer*rr*)r)rNrr)r$fullr r r*arangeZreshapelenrr%_binomial_logpmfrentropyr.r)rnZsupportZ binomial_pmfrrrr9s zMultinomial.entropycountc Cs~|j|jdd}t|d}t|d}t||d}|t||ttt| |}|||||S)NT)Z is_binaryr)rr r$r. _clip_by_zerolog1pr%abs)rr;r"rZfactor_nZfactor_kZ factor_nmkZnormrrrr8s zMultinomial._binomial_logpmf)r r r rr r )r r)r"rr r)rr/r r)r;rr"rr r)__name__ __module__ __qualname____doc____annotations__rpropertyr r!r'r&r1r9r8 __classcell__rrrrrs /     rcCstj|d|dS)Nrr4)r$r6)r;r*rrr_binomial_supportsrFcCs |jdd||jdddS)Nr)min)max)Zclip)xrrrr<s r<) __future__rcollections.abcrtypingrr$Zpaddle.distributionrrr DistributionrrFr<rrrrs   3