o
    hJ                     @   sj   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gZ	dd Z
G d	d
 d
eZG dd deZdS )    N)Function)once_differentiable)constraints)ExponentialFamily	Dirichletc                 C   s8   | dd|}t| ||}||| |  dd  S NT)sum	expand_astorch_dirichlet_grad)xconcentrationgrad_outputtotalgrad r   S/var/www/html/ai/venv/lib/python3.10/site-packages/torch/distributions/dirichlet.py_Dirichlet_backward   s   r   c                   @   s(   e Zd Zedd Zeedd ZdS )
_Dirichletc                 C   s   t |}| || |S N)r   _sample_dirichletsave_for_backward)ctxr   r   r   r   r   forward   s   
z_Dirichlet.forwardc                 C   s   | j \}}t|||S r   )saved_tensorsr   )r   r   r   r   r   r   r   backward   s   
z_Dirichlet.backwardN)__name__
__module____qualname__staticmethodr   r   r   r   r   r   r   r      s    
r   c                       s   e Zd ZdZdeejdiZejZ	dZ
d fdd	Zd fdd		ZdddZdd Zedd Zedd Zedd Zdd Zedd Zdd Z  ZS )r   a  
    Creates a Dirichlet distribution parameterized by concentration :attr:`concentration`.

    Example::

        >>> # xdoctest: +IGNORE_WANT("non-deterinistic")
        >>> m = Dirichlet(torch.tensor([0.5, 0.5]))
        >>> m.sample()  # Dirichlet distributed with concentration [0.5, 0.5]
        tensor([ 0.1046,  0.8954])

    Args:
        concentration (Tensor): concentration parameter of the distribution
            (often referred to as alpha)
    r      TNc                    sN   |  dk r
td|| _|jd d |jdd  }}t j|||d d S )Nr!   z;`concentration` parameter must be at least one-dimensional.r   validate_args)dim
ValueErrorr   shapesuper__init__)selfr   r#   batch_shapeevent_shape	__class__r   r   r(   4   s   zDirichlet.__init__c                    sN   |  t|}t|}| j|| j |_tt|j|| jdd | j	|_	|S )NFr"   )
_get_checked_instancer   r   Sizer   expandr+   r'   r(   _validate_args)r)   r*   	_instancenewr,   r   r   r0   =   s   

zDirichlet.expandr   c                 C   s    |  |}| j|}t|S r   )_extended_shaper   r0   r   apply)r)   sample_shaper&   r   r   r   r   rsampleG   s   

zDirichlet.rsamplec                 C   sL   | j r| | t| jd |dt| jd t| jd S )N      ?r   )r1   _validate_sampler   xlogyr   r	   lgamma)r)   valuer   r   r   log_probL   s   
zDirichlet.log_probc                 C   s   | j | j dd S r   )r   r	   r)   r   r   r   meanU   s   zDirichlet.meanc                 C   sd   | j d jdd}||dd }| j dk jdd}tjj|| jdd|j	d 
|||< |S )Nr!   g        )minr   T)axis)r   clampr	   allr   nn
functionalone_hotargmaxr&   to)r)   concentrationm1modemaskr   r   r   rJ   Y   s   zDirichlet.modec                 C   s0   | j dd}| j || j   |d|d   S )Nr   T   r!   )r   r	   pow)r)   con0r   r   r   variancec   s   zDirichlet.variancec                 C   sb   | j d}| j d}t| j dt| || t|  | j d t| j  d S )Nr   r8   )r   sizer	   r   r;   digamma)r)   ka0r   r   r   entropyl   s   zDirichlet.entropyc                 C   s   | j fS r   )r   r>   r   r   r   _natural_paramsv   s   zDirichlet._natural_paramsc                 C   s   |  dt |d S )Nr   )r;   r	   r   )r)   r   r   r   r   _log_normalizerz   s   zDirichlet._log_normalizerr   )r   )r   r   r   __doc__r   independentpositivearg_constraintssimplexsupporthas_rsampler(   r0   r7   r=   propertyr?   rJ   rO   rT   rU   rV   __classcell__r   r   r,   r   r      s(    	

	

	


)r   torch.autogradr   torch.autograd.functionr   torch.distributionsr   torch.distributions.exp_familyr   __all__r   r   r   r   r   r   r   <module>   s    