o "j-@szddlZddlmZddlZddlZddlmZmZddl m Z ddl m Z ddl mZddlmZGdd d e jZdS) N)Iterable) check_type convert_dtype)Variable) distribution)in_dynamic_mode)randomcsneZdZdZdfdd ZeddZeddZdd d Zdd dZ ddZ ddZ ddZ ddZ ZS)Normala The Normal distribution with location `loc` and `scale` parameters. Mathematical details The probability density function (pdf) is .. math:: pdf(x; \mu, \sigma) = \frac{1}{Z}e^{\frac {-0.5 (x - \mu)^2} {\sigma^2} } .. math:: Z = (2 \pi \sigma^2)^{0.5} In the above equation: * :math:`loc = \mu`: is the mean. * :math:`scale = \sigma`: is the std. * :math:`Z`: is the normalization constant. Args: loc(int|float|list|tuple|numpy.ndarray|Tensor): The mean of normal distribution.The data type is float32 and float64. scale(int|float|list|tuple|numpy.ndarray|Tensor): The std of normal distribution.The data type is float32 and float64. name(str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`. Examples: .. code-block:: python >>> import paddle >>> from paddle.distribution import Normal >>> # Define a single scalar Normal distribution. >>> dist = Normal(loc=0., scale=3.) >>> # Define a batch of two scalar valued Normals. >>> # The first has mean 1 and standard deviation 11, the second 2 and 22. >>> dist = Normal(loc=[1., 2.], scale=[11., 22.]) >>> # Get 3 samples, returning a 3 x 2 tensor. >>> dist.sample([3]) >>> # Define a batch of two scalar valued Normals. >>> # Both have mean 1, but different standard deviations. >>> dist = Normal(loc=1., scale=[11., 22.]) >>> # Complete example >>> value_tensor = paddle.to_tensor([0.8], dtype="float32") >>> normal_a = Normal([0.], [1.]) >>> normal_b = Normal([0.5], [2.]) >>> sample = normal_a.sample([2]) >>> # a random tensor created by normal distribution with shape: [2, 1] >>> entropy = normal_a.entropy() >>> print(entropy) Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True, [1.41893852]) >>> lp = normal_a.log_prob(value_tensor) >>> print(lp) Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True, [-1.23893857]) >>> p = normal_a.probs(value_tensor) >>> print(p) Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True, [0.28969154]) >>> kl = normal_a.kl_divergence(normal_b) >>> print(kl) Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True, [0.34939718]) Nc shtst|dtttjtttfdt|dtttjtttfdd|_ |dur(|nd|_ d|_ t |tr7t|}t |tr@t|}| ||rS||_||_t|j |_ nWt |tr`t |tr`d|_ t |tjrrt|j dvrr|j |_ nt |tjrt|j dvr|j |_ |||\|_|_|j t|jj krtj|j|j d|_tj|j|j d|_t|jjdS) Nlocr scaleFfloat32T)r Zfloat64dtype)rrintfloatnpZndarrayrlisttupleall_arg_is_floatnamer isinstanceZ_validate_argsr r rstrZ _to_tensorpaddlecastsuper__init__shape)selfr r r __class__[/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/paddle/distribution/normal.pyrasF    zNormal.__init__cCs|jS)z[Mean of multinomial distribuion. Returns: Tensor: mean value. )r rr r r!meansz Normal.meancCs |jdS)zbVariance of lognormal distribution. Returns: Tensor: variance value. )r powr"r r r!variances zNormal.variancer rc CsDt|ts tdtst|dtdt|}t|j|jj }|j d}d|vrr||}t||}t |j|jd |d<t |d|j}t ||}t |} tj| dd||jd } | ||j} t j| |j|d } | S||}tj|dd||jd t j||jd |j} t j| |j|d } |jrt j| ||d S| S) a&Generate samples of the specified shape. Args: shape (Sequence[int], optional): Shape of the generated samples. seed (int): Python integer number. Returns: Tensor, A tensor with prepended dimensions shape.The data type is float32. %sample shape must be Iterable object.seedsample_sampler?)r#Zstdr(rrr )rr TypeErrorrrrrr r rrritemfullrZreshaperZgaussianaddZzerosr) rrr( batch_shaperZ output_shape fill_shapezero_tmpZzero_tmp_reshapeZzero_tmp_shapeZnormal_random_tmpoutputr r r!r)s<       z Normal.samplecCs<t|ts td|t|}tj|d}|j||jS)aGenerate reparameterized samples of the specified shape. Args: shape (Sequence[int], optional): Shape of the generated samples. Returns: Tensor: A tensor with prepended dimensions shape.The data type is float32. r')r) rrr/Z _extend_shaperrnormalr r )rrepsr r r!rsamples  zNormal.rsamplecCs|jd}t|j|jj}d|vr4t|}t|j|jd|d<|j|jj}t|d|}nt|d|j}tj d|dt dt j t |j||dS)a>Shannon entropy in nats. The entropy is .. math:: entropy(\sigma) = 0.5 \log (2 \pi e \sigma^2) In the above equation: * :math:`scale = \sigma`: is the std. Returns: Tensor, Shannon entropy of normal distribution.The data type is float32. Z_entropyr+rr,?r$r.) rrr r rrr0rr1r2mathlogpi)rrr3r4Z fill_dtyper5r r r!entropys "zNormal.entropyc Csr|jd}||j|}|j|j}t|j}tjd||j||jd||ttdtj |dS)zLog probability density/mass function. Args: value (Tensor): The input tensor. Returns: Tensor: log probability.The data type is same with :attr:`value` . Z _log_prob@r.) r_check_values_dtype_in_probsr r rr<subtractr;sqrtr=)rvaluervarZ log_scaler r r!log_probs   zNormal.log_probcCsh|jd}||j|}|j|j}tjtd||j||jd|tdtj |j|dS)zProbability density/mass function. Args: value (Tensor): The input tensor. Returns: Tensor, probability. The data type is same with :attr:`value` . Z_probsr?r@r$r.) rrAr r rdivideexpr;rCr=)rrDrrEr r r!probss  z Normal.probscCsrts t|dtd|jd}|j|j}||}|j|j|j}||}tjd|d|dt||dS)aThe KL-divergence between two normal distributions. The probability density function (pdf) is .. math:: KL\_divergence(\mu_0, \sigma_0; \mu_1, \sigma_1) = 0.5 (ratio^2 + (\frac{diff}{\sigma_1})^2 - 1 - 2 \ln {ratio}) .. math:: ratio = \frac{\sigma_0}{\sigma_1} .. math:: diff = \mu_1 - \mu_0 In the above equation: * :math:`loc = \mu_0`: is the mean of current Normal distribution. * :math:`scale = \sigma_0`: is the std of current Normal distribution. * :math:`loc = \mu_1`: is the mean of other Normal distribution. * :math:`scale = \sigma_1`: is the std of other Normal distribution. * :math:`ratio`: is the ratio of scales. * :math:`diff`: is the difference between means. Args: other (Normal): instance of Normal. Returns: Tensor, kl-divergence between two normal distributions.The data type is float32. other kl_divergenceZ_kl_divergencer:r-r.) rrr rr r rr2r<)rrJrZ var_ratiot1r r r!rK+s!  zNormal.kl_divergence)N)r r)r )__name__ __module__ __qualname____doc__rpropertyr#r&r)r9r>rFrIrK __classcell__r r rr!r sD/    - r )r;collections.abcrnumpyrrZpaddle.base.data_feederrrZpaddle.base.frameworkrZpaddle.distributionrZpaddle.frameworkrZ paddle.tensorr Distributionr r r r r!s