o
    h!                     @   sv   d dl Z d dlmZ d dl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gZG dd deZdS )	    N)Number)constraints)ExponentialFamily)broadcast_allclamp_probslazy_propertylogits_to_probsprobs_to_logits) binary_cross_entropy_with_logitsContinuousBernoullic                       s
  e Zd ZdZejejdZejZdZ	dZ
	d/ fdd	Zd0 fd	d
	Zdd Zdd Zdd Zdd Zedd Zedd Zedd Zedd Zedd Zedd Ze fdd Ze fd!d"Zd#d$ Zd%d& Zd'd( Zd)d* Z ed+d, Z!d-d. Z"  Z#S )1r   a  
    Creates a continuous Bernoulli distribution parameterized by :attr:`probs`
    or :attr:`logits` (but not both).

    The distribution is supported in [0, 1] and parameterized by 'probs' (in
    (0,1)) or 'logits' (real-valued). Note that, unlike the Bernoulli, 'probs'
    does not correspond to a probability and 'logits' does not correspond to
    log-odds, but the same names are used due to the similarity with the
    Bernoulli. See [1] for more details.

    Example::

        >>> # xdoctest: +IGNORE_WANT("non-deterinistic")
        >>> m = ContinuousBernoulli(torch.tensor([0.3]))
        >>> m.sample()
        tensor([ 0.2538])

    Args:
        probs (Number, Tensor): (0,1) valued parameters
        logits (Number, Tensor): real valued parameters whose sigmoid matches 'probs'

    [1] The continuous Bernoulli: fixing a pervasive error in variational
    autoencoders, Loaiza-Ganem G and Cunningham JP, NeurIPS 2019.
    https://arxiv.org/abs/1907.06845
    )probslogitsr   TNgV-?gx&1?c                    s   |d u |d u krt d|d ur5t|t}t|\| _|d ur.| jd | j s.t dt| j| _nt|t}t|\| _	|d urG| jn| j	| _
|rRt }n| j
 }|| _t j||d d S )Nz;Either `probs` or `logits` must be specified, but not both.r   z&The parameter probs has invalid valuesvalidate_args)
ValueError
isinstancer   r   r   arg_constraintscheckallr   r   _paramtorchSizesize_limssuper__init__)selfr   r   limsr   	is_scalarbatch_shape	__class__ ^/var/www/html/ai/venv/lib/python3.10/site-packages/torch/distributions/continuous_bernoulli.pyr   2   s&   



zContinuousBernoulli.__init__c                    s~   |  t|}| j|_t|}d| jv r| j||_|j|_d| jv r/| j	||_	|j	|_t
t|j|dd | j|_|S )Nr   r   Fr   )_get_checked_instancer   r   r   r   __dict__r   expandr   r   r   r   _validate_args)r   r    	_instancenewr!   r#   r$   r'   M   s   


zContinuousBernoulli.expandc                 O   s   | j j|i |S N)r   r*   )r   argskwargsr#   r#   r$   _new[   s   zContinuousBernoulli._newc                 C   s,   t t | j| jd t | j| jd S )Nr      )r   maxler   r   gtr   r#   r#   r$   _outside_unstable_region^   s   $z,ContinuousBernoulli._outside_unstable_regionc                 C   s&   t |  | j| jd t | j S )Nr   )r   wherer4   r   r   	ones_liker3   r#   r#   r$   
_cut_probsc   s
   zContinuousBernoulli._cut_probsc              	   C   s   |   }tt|d|t|}tt|d|t|}ttt	| t| tt|dt	d| td| d  }t
| jd d}tddd|  |  }t|  ||S )zLcomputes the log normalizing constant as a function of the 'probs' parameter      ?g              @      ?   gUUUUUU?g'}'}@)r7   r   r5   r1   
zeros_likeger6   logabslog1ppowr   mathr4   )r   	cut_probscut_probs_below_halfcut_probs_above_halflog_normxtaylorr#   r#   r$   _cont_bern_log_normj   s&   
z'ContinuousBernoulli._cont_bern_log_normc                 C   sj   |   }|d| d  dt| t|   }| jd }dddt|d  |  }t|  ||S )Nr9   r:   r8   gUUUUUU?gll?r;   )r7   r   r@   r>   r   rA   r5   r4   )r   rC   musrG   rH   r#   r#   r$   mean~   s   
zContinuousBernoulli.meanc                 C   s   t | jS r+   )r   sqrtvariancer3   r#   r#   r$   stddev   s   zContinuousBernoulli.stddevc                 C   s   |   }||d  tdd|  d dtt| t| d  }t| jd d}ddd|  |  }t|  ||S )Nr:   r9   r;   r8   gUUUUUU?g?ggjV?)r7   r   rA   r@   r>   r   r5   r4   )r   rC   varsrG   rH   r#   r#   r$   rM      s    zContinuousBernoulli.variancec                 C   s   t | jddS NT)	is_binary)r	   r   r3   r#   r#   r$   r      s   zContinuousBernoulli.logitsc                 C   s   t t| jddS rP   )r   r   r   r3   r#   r#   r$   r      s   zContinuousBernoulli.probsc                 C   s
   | j  S r+   )r   r   r3   r#   r#   r$   param_shape   s   
zContinuousBernoulli.param_shapec                 C   sX   |  |}tj|| jj| jjd}t  | |W  d    S 1 s%w   Y  d S N)dtypedevice)_extended_shaper   randr   rT   rU   no_gradicdfr   sample_shapeshapeur#   r#   r$   sample   s
   

$zContinuousBernoulli.samplec                 C   s,   |  |}tj|| jj| jjd}| |S rS   )rV   r   rW   r   rT   rU   rY   rZ   r#   r#   r$   rsample   s   

zContinuousBernoulli.rsamplec                 C   s8   | j r| | t| j|\}}t||dd |   S )Nnone)	reduction)r(   _validate_sampler   r   r
   rI   )r   valuer   r#   r#   r$   log_prob   s   
zContinuousBernoulli.log_probc              
   C   s   | j r| | |  }t||td| d|  | d d| d  }t|  ||}tt|dt|tt	|dt
||S )Nr:   r9   g        )r(   rb   r7   r   rA   r5   r4   r1   r<   r=   r6   )r   rc   rC   cdfsunbounded_cdfsr#   r#   r$   cdf   s    


zContinuousBernoulli.cdfc              	   C   sT   |   }t|  t| |d| d   t|  t|t|   |S )Nr9   r:   )r7   r   r5   r4   r@   r>   )r   rc   rC   r#   r#   r$   rY      s   
zContinuousBernoulli.icdfc                 C   s4   t | j }t | j}| j||  |   | S r+   )r   r@   r   r>   rK   rI   )r   
log_probs0
log_probs1r#   r#   r$   entropy   s   zContinuousBernoulli.entropyc                 C   s   | j fS r+   )r   r3   r#   r#   r$   _natural_params   s   z#ContinuousBernoulli._natural_paramsc                 C   s   t t || jd d t || jd d }t ||| jd d t | }t t t 	|d t t | }d| t 
|dd  t 
|dd  }t |||S )	zLcomputes the log normalizing constant as a function of the natural parameterr   r8   r/   r:   r;   g      8@   g     @)r   r0   r1   r   r2   r5   r6   r>   r?   exprA   )r   rG   out_unst_regcut_nat_paramsrF   rH   r#   r#   r$   _log_normalizer   s   ((z#ContinuousBernoulli._log_normalizer)NNr   Nr+   )$__name__
__module____qualname____doc__r   unit_intervalrealr   support_mean_carrier_measurehas_rsampler   r'   r.   r4   r7   rI   propertyrK   rN   rM   r   r   r   rR   r   r   r^   r_   rd   rg   rY   rj   rk   rp   __classcell__r#   r#   r!   r$   r      sD    
	

	


		
)rB   numbersr   r   torch.distributionsr   torch.distributions.exp_familyr   torch.distributions.utilsr   r   r   r   r	   torch.nn.functionalr
   __all__r   r#   r#   r#   r$   <module>   s    