o
    ߗiM                     @   s   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	 d	eZG d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                       s   e Zd ZdZejejdZejZd fdd	Z	d fdd	Z
dd	 Zed
d Zedd Zedd Ze fdedejfddZdd Z  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                    s   || _ |d u |d u krtd|d urt|t}t|\| _nt|t}t|\| _|d ur1| jn| j| _|r<t	 }n| j
 }t j||d 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__ c/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/torch/distributions/relaxed_bernoulli.pyr   ,   s   



zLogitRelaxedBernoulli.__init__c                    s~   |  t|}t|}| j|_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LogitRelaxedBernoulli.expandc                 O   s   | j j|i |S N)r   r*   )r   argskwargsr"   r"   r#   _newM   s   zLogitRelaxedBernoulli._newc                 C      t | jddS NT)	is_binary)r   r   r   r"   r"   r#   r   P      zLogitRelaxedBernoulli.logitsc                 C   r/   r0   )r
   r   r2   r"   r"   r#   r   T   r3   zLogitRelaxedBernoulli.probsc                 C   s
   | j  S r+   )r   r   r2   r"   r"   r#   param_shapeX   s   
z!LogitRelaxedBernoulli.param_shapesample_shapereturnc                 C   s\   |  |}t| j|}ttj||j|jd}| | 	  |  | 	  | j
 S )N)dtypedevice)_extended_shaper   r   r&   r   randr7   r8   loglog1pr   )r   r5   shaper   uniformsr"   r"   r#   rsample\   s   
"zLogitRelaxedBernoulli.rsamplec                 C   sN   | j r| | t| j|\}}||| j }| j | d|    S )N   )	r'   _validate_sampler   r   mulr   r;   expr<   )r   valuer   diffr"   r"   r#   log_probf   s
   
zLogitRelaxedBernoulli.log_probNNNr+   )__name__
__module____qualname____doc__r   unit_intervalrealarg_constraintssupportr   r&   r.   r	   r   r   propertyr4   r   r   r   Tensorr?   rF   __classcell__r"   r"   r    r#   r      s    



c                       sl   e Zd ZdZejejdZejZdZ	d fdd	Z
d fdd	Zed	d
 Zedd Zedd Z  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                    s$   t |||}t j|t |d d S )Nr   )r   r   r   r   )r   r   r   r   r   	base_distr    r"   r#   r      s   zRelaxedBernoulli.__init__c                    s   |  t|}t j||dS )N)r)   )r$   r   r   r&   r(   r    r"   r#   r&      s   zRelaxedBernoulli.expandc                 C      | j jS r+   )rS   r   r2   r"   r"   r#   r         zRelaxedBernoulli.temperaturec                 C   rT   r+   )rS   r   r2   r"   r"   r#   r      rU   zRelaxedBernoulli.logitsc                 C   rT   r+   )rS   r   r2   r"   r"   r#   r      rU   zRelaxedBernoulli.probsrG   r+   )rH   rI   rJ   rK   r   rL   rM   rN   rO   has_rsampler   r&   rP   r   r   r   rR   r"   r"   r    r#   r   n   s    

)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"   r"   r#   <module>   s   X