a
    h	                     @   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 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 )    )OptionalN)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e
ee
 ee
 ee dd fddZd fdd		Zd
d ZeejdddZee
dddZee
dddZe fee
d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logitsTNtemperaturer   r   validate_argsreturnc                    s@   t ||| _|| _| jj}| jjdd  }t j|||d d S )Nr   )r   _categoricalr   batch_shapeparam_shapesuper__init__)selfr   r   r   r   r   event_shape	__class__ U/var/www/auris/lib/python3.9/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%   <   s    

zExpRelaxedCategorical.expandc                 O   s   | j j|i |S N)r   _new)r   argskwargsr    r    r!   r+   G   s    zExpRelaxedCategorical._newr   c                 C   s   | j jS r*   )r   r   r   r    r    r!   r   J   s    z!ExpRelaxedCategorical.param_shapec                 C   s   | j jS r*   )r   r   r/   r    r    r!   r   N   s    zExpRelaxedCategorical.logitsc                 C   s   | j jS r*   )r   r   r/   r    r    r!   r   R   s    zExpRelaxedCategorical.probs)sample_shaper   c                 C   sX   |  |}ttj|| jj| jjd}|    }| j| | j }||j	ddd S )N)dtypedevicer   TZdimZkeepdim)
Z_extended_shaper
   r#   Zrandr   r1   r2   logr   	logsumexp)r   r0   shapeZuniformsZgumbelsZscoresr    r    r!   rsampleV   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   Tr3   )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_prob_   s    

zExpRelaxedCategorical.log_prob)NNN)N)__name__
__module____qualname____doc__r   simplexreal_vectorarg_constraintssupporthas_rsampler   r   boolr   r%   r+   propertyr#   r$   r   r   r   r   r7   r?   __classcell__r    r    r   r!   r      s2      	c                       s   e Zd ZU dZejejdZejZdZ	e
ed< deee ee ee dd fddZd fd	d
	ZeedddZeedddZeed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   T	base_distNr   c                    s(   t ||||d}t j|t |d d S )Nr   )r   r   r   r   )r   r   r   r   r   rL   r   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   s   | j jS r*   )rL   r   r/   r    r    r!   r      s    z$RelaxedOneHotCategorical.temperaturec                 C   s   | j jS r*   )rL   r   r/   r    r    r!   r      s    zRelaxedOneHotCategorical.logitsc                 C   s   | j jS r*   )rL   r   r/   r    r    r!   r      s    zRelaxedOneHotCategorical.probs)NNN)N)r@   rA   rB   rC   r   rD   rE   rF   rG   rH   r   __annotations__r   r   rI   r   r%   rJ   r   r   r   rK   r    r    r   r!   r   l   s,   
   )typingr   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   Z