
    קgM                         d dl mZ d dlZd dlmZ d dlmZ d dlmZ d dl	m
Z
 d dlmZmZmZmZmZ d dlmZ d	d
gZ G d d	e          Z G d d
e          ZdS )    )NumberN)constraints)Distribution)TransformedDistribution)SigmoidTransform)broadcast_allclamp_probslazy_propertylogits_to_probsprobs_to_logits)_sizeLogitRelaxedBernoulliRelaxedBernoullic                        e Zd ZdZej        ej        dZej        Zd fd	Z	d fd	Z
d Zed             Zed             Zed	             Z ej                    fd
edej        fdZd Z xZS )r   a  
    Creates a LogitRelaxedBernoulli distribution parameterized by :attr:`probs`
    or :attr:`logits` (but not both), which is the logit of a RelaxedBernoulli
    distribution.

    Samples are logits of values in (0, 1). See [1] for more details.

    Args:
        temperature (Tensor): relaxation temperature
        probs (Number, Tensor): the probability of sampling `1`
        logits (Number, Tensor): the log-odds of sampling `1`

    [1] The Concrete Distribution: A Continuous Relaxation of Discrete Random
    Variables (Maddison et al., 2017)

    [2] Categorical Reparametrization with Gumbel-Softmax
    (Jang et al., 2017)
    probslogitsNc                    || _         |d u |d u k    rt          d          |,t          |t                    }t	          |          \  | _        n+t          |t                    }t	          |          \  | _        || j        n| j        | _        |rt          j	                    }n| j        
                                }t                                          ||           d S )Nz;Either `probs` or `logits` must be specified, but not both.validate_args)temperature
ValueError
isinstancer   r   r   r   _paramtorchSizesizesuper__init__)selfr   r   r   r   	is_scalarbatch_shape	__class__s          a/var/www/html/ai-engine/env/lib/python3.11/site-packages/torch/distributions/relaxed_bernoulli.pyr   zLogitRelaxedBernoulli.__init__,   s    &TMv~..M   "5&11I)%00MTZZ"6622I*622NT[$)$5djj4; 	-*,,KK+**,,KMBBBBB    c                    |                      t          |          }t          j        |          }| j        |_        d| j        v r+| j                            |          |_        |j        |_        d| j        v r+| j	                            |          |_	        |j	        |_        t          t          |                              |d           | j        |_        |S )Nr   r   Fr   )_get_checked_instancer   r   r   r   __dict__r   expandr   r   r   r   _validate_argsr    r"   	_instancenewr#   s       r$   r)   zLogitRelaxedBernoulli.expand?   s    (()>	JJj--*dm##
))+66CICJt}$$++K88CJCJ#S))22;e2TTT!0
r%   c                 &     | j         j        |i |S N)r   r-   )r    argskwargss      r$   _newzLogitRelaxedBernoulli._newM   s    t{////r%   c                 .    t          | j        d          S NT)	is_binary)r   r   r    s    r$   r   zLogitRelaxedBernoulli.logitsP   s    tzT::::r%   c                 .    t          | j        d          S r4   )r   r   r6   s    r$   r   zLogitRelaxedBernoulli.probsT   s    t{d;;;;r%   c                 4    | j                                         S r/   )r   r   r6   s    r$   param_shapez!LogitRelaxedBernoulli.param_shapeX   s    {!!!r%   sample_shapereturnc                    |                      |          }t          | j                            |                    }t          t	          j        ||j        |j                            }|                                | 	                                z
  |                                z   | 	                                z
  | j
        z  S )N)dtypedevice)_extended_shaper	   r   r)   r   randr=   r>   loglog1pr   )r    r:   shaper   uniformss        r$   rsamplezLogitRelaxedBernoulli.rsample\   s    $$\22DJ--e4455JuEKEEE
 
 LLNNxi..000599;;>5&AQAQQ 	r%   c                 0   | j         r|                     |           t          | j        |          \  }}||                    | j                  z
  }| j                                        |z   d|                                                                z  z
  S )N   )	r*   _validate_sampler   r   mulr   rA   exprB   )r    valuer   diffs       r$   log_probzLogitRelaxedBernoulli.log_probf   s     	)!!%(((%dk599		$"2333##%%,q488::3C3C3E3E/EEEr%   NNNr/   )__name__
__module____qualname____doc__r   unit_intervalrealarg_constraintssupportr   r)   r2   r
   r   r   propertyr9   r   r   r   TensorrE   rM   __classcell__r#   s   @r$   r   r      s4        $ !, 9[EUVVOGC C C C C C&     0 0 0 ; ; ]; < < ]< " " X" -7EJLL  E U\    F F F F F F Fr%   c                        e Zd ZdZej        ej        dZej        ZdZ	d
 fd	Z
d fd	Zed             Zed             Zed	             Z xZS )r   a  
    Creates a RelaxedBernoulli distribution, parametrized by
    :attr:`temperature`, and either :attr:`probs` or :attr:`logits`
    (but not both). This is a relaxed version of the `Bernoulli` distribution,
    so the values are in (0, 1), and has reparametrizable samples.

    Example::

        >>> # xdoctest: +IGNORE_WANT("non-deterministic")
        >>> m = RelaxedBernoulli(torch.tensor([2.2]),
        ...                      torch.tensor([0.1, 0.2, 0.3, 0.99]))
        >>> m.sample()
        tensor([ 0.2951,  0.3442,  0.8918,  0.9021])

    Args:
        temperature (Tensor): relaxation temperature
        probs (Number, Tensor): the probability of sampling `1`
        logits (Number, Tensor): the log-odds of sampling `1`
    r   TNc                     t          |||          }t                                          |t                      |           d S )Nr   )r   r   r   r   )r    r   r   r   r   	base_distr#   s         r$   r   zRelaxedBernoulli.__init__   s@    )+ufEE	$4$6$6mTTTTTr%   c                     |                      t          |          }t                                          ||          S )N)r,   )r'   r   r   r)   r+   s       r$   r)   zRelaxedBernoulli.expand   s3    (()99EEww~~kS~999r%   c                     | j         j        S r/   )r]   r   r6   s    r$   r   zRelaxedBernoulli.temperature   s    ~))r%   c                     | j         j        S r/   )r]   r   r6   s    r$   r   zRelaxedBernoulli.logits   s    ~$$r%   c                     | j         j        S r/   )r]   r   r6   s    r$   r   zRelaxedBernoulli.probs   s    ~##r%   rN   r/   )rO   rP   rQ   rR   r   rS   rT   rU   rV   has_rsampler   r)   rW   r   r   r   rY   rZ   s   @r$   r   r   n   s         & !, 9[EUVVO'GKU U U U U U: : : : : : * * X* % % X% $ $ X$ $ $ $ $r%   )numbersr   r   torch.distributionsr    torch.distributions.distributionr   ,torch.distributions.transformed_distributionr   torch.distributions.transformsr   torch.distributions.utilsr   r	   r
   r   r   torch.typesr   __all__r   r    r%   r$   <module>rl      s?          + + + + + + 9 9 9 9 9 9 P P P P P P ; ; ; ; ; ;                    #$6
7UF UF UF UF UFL UF UF UFp*$ *$ *$ *$ *$. *$ *$ *$ *$ *$r%   