o
    eiR$                     @   s   d dl Z d dlZd dlmZ d dlmZ d dlmZ d dlmZm	Z	m
Z
mZmZ d dlmZ d dlmZmZmZ dgZG d	d deZdS )
    N)Tensor)constraints)ExponentialFamily)broadcast_allclamp_probslazy_propertylogits_to_probsprobs_to_logits) binary_cross_entropy_with_logits)_Number_sizeNumberContinuousBernoullic                       s|  e Zd ZdZejejdZejZdZ	dZ
				d5deeB dB deeB dB d	eeef d
edB ddf
 fddZd6 fdd	Zdd Zdd Zdd Zdd ZedefddZedefddZedefddZedefddZedefd d!Zedejfd"d#Ze fd$d%Z e fd&e!defd'd(Z"d)d* Z#d+d, Z$d-d. Z%d/d0 Z&edee fd1d2Z'd3d4 Z(  Z)S )7r   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-deterministic")
        >>> 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?r   r   limsvalidate_argsreturnc                    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|d u r=t	dt|t}t|\| _
|d urO| jn| j
| _|rZt }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 valueszlogits is unexpectedly Noner   )
ValueError
isinstancer   r   r   arg_constraintscheckallr   AssertionErrorr   _paramtorchSizesize_limssuper__init__)selfr   r   r   r   	is_scalarbatch_shape	__class__ r/var/www/addictedbytheproject.nl/epg/venv/lib/python3.10/site-packages/torch/distributions/continuous_bernoulli.pyr"   7   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,   [   s   


zContinuousBernoulli.expandc                 O   s   | j j|i |S N)r   r/   )r#   argskwargsr(   r(   r)   _newi   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_regionl   s   $z,ContinuousBernoulli._outside_unstable_regionc                 C   s&   t |  | j| jd t | j S )Nr   )r   wherer9   r   r    	ones_liker8   r(   r(   r)   
_cut_probsq   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'}'}@)r<   r   r:   r6   
zeros_likeger;   logabslog1ppowr   mathr9   )r#   	cut_probscut_probs_below_halfcut_probs_above_halflog_normxtaylorr(   r(   r)   _cont_bern_log_normx   s&   
z'ContinuousBernoulli._cont_bern_log_normc                 C   sj   |   }|d| d  dt| t|   }| jd }dddt|d  |  }t|  ||S )Nr>   r?   r=   gUUUUUU?gll?r@   )r<   r   rE   rC   r   rF   r:   r9   )r#   rH   musrL   rM   r(   r(   r)   mean   s   
zContinuousBernoulli.meanc                 C   s   t | jS r0   )r   sqrtvariancer8   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?   r>   r@   r=   gUUUUUU?g?ggjV?)r<   r   rF   rE   rC   r   r:   r9   )r#   rH   varsrL   rM   r(   r(   r)   rR      s    zContinuousBernoulli.variancec                 C   s   t | jddS NT)	is_binary)r	   r   r8   r(   r(   r)   r      s   zContinuousBernoulli.logitsc                 C   s   t t| jddS rU   )r   r   r   r8   r(   r(   r)   r      s   zContinuousBernoulli.probsc                 C   s
   | j  S r0   )r   r   r8   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   rY   rZ   no_gradicdfr#   sample_shapeshapeur(   r(   r)   sample   s
   

$zContinuousBernoulli.sampler`   c                 C   s,   |  |}tj|| jj| jjd}| |S rX   )r[   r   r\   r   rY   rZ   r^   r_   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
   rN   )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?   r>   g        )r-   rg   r<   r   rF   r:   r9   r6   rA   rB   r;   )r#   rh   rH   cdfsunbounded_cdfsr(   r(   r)   cdf   s    


zContinuousBernoulli.cdfc              	   C   sT   |   }t|  t| |d| d   t|  t|t|   |S )Nr>   r?   )r<   r   r:   r9   rE   rC   )r#   rh   rH   r(   r(   r)   r^      s   
zContinuousBernoulli.icdfc                 C   s4   t | j }t | j}| j||  |   | S r0   )r   rE   r   rC   rP   rN   )r#   
log_probs0
log_probs1r(   r(   r)   entropy   s   zContinuousBernoulli.entropyc                 C   s   | j fS r0   )r   r8   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 j	
|t t | }d| t |dd  t |dd  }t |||S )zLcomputes the log normalizing constant as a function of the natural parameterr   r=   r4   r@   g      8@   g     @)r   r5   r6   r    r7   r:   r;   rC   rD   specialexpm1rF   )r#   rL   out_unst_regcut_nat_paramsrK   rM   r(   r(   r)   _log_normalizer   s   ((z#ContinuousBernoulli._log_normalizer)NNr   Nr0   )*__name__
__module____qualname____doc__r   unit_intervalrealr   support_mean_carrier_measurehas_rsampler   r   tuplefloatboolr"   r,   r3   r9   r<   rN   propertyrP   rS   rR   r   r   r   r   r   rW   rc   r   rd   ri   rl   r^   ro   rp   rv   __classcell__r(   r(   r&   r)   r      s^    


$				)rG   r   r   torch.distributionsr   torch.distributions.exp_familyr   torch.distributions.utilsr   r   r   r   r	   torch.nn.functionalr
   torch.typesr   r   r   __all__r   r(   r(   r(   r)   <module>   s   