o
    Zh                     @   s   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	 d dl
mZ d dl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 )    N)Tensor)constraints)Categorical)Distribution)TransformedDistribution)ExpTransform)broadcast_allclamp_probs)_sizeExpRelaxedCategoricalRelaxedOneHotCategoricalc                       s   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d	d
 ZedejfddZedefddZedefddZe fdedefddZdd Z  ZS )r   a  
    Creates a ExpRelaxedCategorical parameterized by
    :attr:`temperature`, and either :attr:`probs` or :attr:`logits` (but not both).
    Returns the log of a point in the simplex. Based on the interface to
    :class:`OneHotCategorical`.

    Implementation based on [1].

    See also: :func:`torch.distributions.OneHotCategorical`

    Args:
        temperature (Tensor): relaxation temperature
        probs (Tensor): event probabilities
        logits (Tensor): unnormalized log probability for each event

    [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logitsTNc                    s@   t ||| _|| _| jj}| jjdd  }t j|||d d S )Nvalidate_args)r   _categoricaltemperaturebatch_shapeparam_shapesuper__init__)selfr   r   r   r   r   event_shape	__class__ V/var/www/auris/lib/python3.10/site-packages/torch/distributions/relaxed_categorical.pyr   -   s
   zExpRelaxedCategorical.__init__c                    sP   |  t|}t|}| j|_| j||_tt|j|| j	dd | j
|_
|S )NFr   )_get_checked_instancer   torchSizer   r   expandr   r   r   _validate_argsr   r   	_instancenewr   r   r   r"   4   s   

zExpRelaxedCategorical.expandc                 O   s   | j j|i |S N)r   _new)r   argskwargsr   r   r   r(   ?   s   zExpRelaxedCategorical._newreturnc                 C      | j jS r'   )r   r   r   r   r   r   r   B      z!ExpRelaxedCategorical.param_shapec                 C   r,   r'   )r   r   r-   r   r   r   r   F   r.   zExpRelaxedCategorical.logitsc                 C   r,   r'   )r   r   r-   r   r   r   r   J   r.   zExpRelaxedCategorical.probssample_shapec                 C   sX   |  |}ttj|| jj| jjd}|    }| j| | j }||j	ddd S )N)dtypedevicer   TdimZkeepdim)
Z_extended_shaper	   r    Zrandr   r0   r1   logr   	logsumexp)r   r/   shapeZuniformsZgumbelsZscoresr   r   r   rsampleN   s   
zExpRelaxedCategorical.rsamplec                 C   s   | j j}| jr| | t| j|\}}t| jt	|
 | j |d   }||| j }||jddd d}|| S )N   r   Tr2   )r   Z_num_eventsr#   Z_validate_sampler   r   r    Z	full_liker   floatlgammar4   mulr5   sum)r   valueKr   Z	log_scaleZscorer   r   r   log_probW   s   

zExpRelaxedCategorical.log_probNNNr'   )__name__
__module____qualname____doc__r   simplexreal_vectorarg_constraintssupporthas_rsampler   r"   r(   propertyr    r!   r   r   r   r   r
   r7   r?   __classcell__r   r   r   r   r      s"    	c                       s~   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	efd
dZed	efddZed	efddZ  ZS )r   a  
    Creates a RelaxedOneHotCategorical distribution parametrized by
    :attr:`temperature`, and either :attr:`probs` or :attr:`logits`.
    This is a relaxed version of the :class:`OneHotCategorical` distribution, so
    its samples are on simplex, and are reparametrizable.

    Example::

        >>> # xdoctest: +IGNORE_WANT("non-deterministic")
        >>> m = RelaxedOneHotCategorical(torch.tensor([2.2]),
        ...                              torch.tensor([0.1, 0.2, 0.3, 0.4]))
        >>> m.sample()
        tensor([ 0.1294,  0.2324,  0.3859,  0.2523])

    Args:
        temperature (Tensor): relaxation temperature
        probs (Tensor): event probabilities
        logits (Tensor): unnormalized log probability for each event
    r   TNc                    s(   t ||||d}t j|t |d d S )Nr   )r   r   r   r   )r   r   r   r   r   	base_distr   r   r   r   }   s   z!RelaxedOneHotCategorical.__init__c                    s   |  t|}t j||dS )N)r%   )r   r   r   r"   r$   r   r   r   r"      s   zRelaxedOneHotCategorical.expandr+   c                 C   r,   r'   )rL   r   r-   r   r   r   r      r.   z$RelaxedOneHotCategorical.temperaturec                 C   r,   r'   )rL   r   r-   r   r   r   r      r.   zRelaxedOneHotCategorical.logitsc                 C   r,   r'   )rL   r   r-   r   r   r   r      r.   zRelaxedOneHotCategorical.probsr@   r'   )rA   rB   rC   rD   r   rE   rF   rG   rH   rI   r   r"   rJ   r   r   r   r   rK   r   r   r   r   r   d   s    )r    r   Ztorch.distributionsr   Ztorch.distributions.categoricalr   Z torch.distributions.distributionr   Z,torch.distributions.transformed_distributionr   Ztorch.distributions.transformsr   Ztorch.distributions.utilsr   r	   Ztorch.typesr
   __all__r   r   r   r   r   r   <module>   s   T