o
    ߗiP                     @   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gZG dd deZdS )	    )DictN)constraints)Distribution)_sum_rightmost)_sizeIndependentc                       s   e Zd ZU dZi Zeeejf e	d< 	d# fdd	Z
d# fdd	Zedd	 Zed
d Zejdd Zedd Zedd Zedd Ze fddZe fdedejfddZdd Zdd Zd$dd Zd!d" Z  ZS )%r   a  
    Reinterprets some of the batch dims of a distribution as event dims.

    This is mainly useful for changing the shape of the result of
    :meth:`log_prob`. For example to create a diagonal Normal distribution with
    the same shape as a Multivariate Normal distribution (so they are
    interchangeable), you can::

        >>> from torch.distributions.multivariate_normal import MultivariateNormal
        >>> from torch.distributions.normal import Normal
        >>> loc = torch.zeros(3)
        >>> scale = torch.ones(3)
        >>> mvn = MultivariateNormal(loc, scale_tril=torch.diag(scale))
        >>> [mvn.batch_shape, mvn.event_shape]
        [torch.Size([]), torch.Size([3])]
        >>> normal = Normal(loc, scale)
        >>> [normal.batch_shape, normal.event_shape]
        [torch.Size([3]), torch.Size([])]
        >>> diagn = Independent(normal, 1)
        >>> [diagn.batch_shape, diagn.event_shape]
        [torch.Size([]), torch.Size([3])]

    Args:
        base_distribution (torch.distributions.distribution.Distribution): a
            base distribution
        reinterpreted_batch_ndims (int): the number of batch dims to
            reinterpret as event dims
    arg_constraintsNc                    s   |t |jkrtd| dt |j |j|j }|t |j }|d t ||  }|t || d  }|| _|| _t j|||d d S )NzQExpected reinterpreted_batch_ndims <= len(base_distribution.batch_shape), actual z vs validate_args)lenbatch_shape
ValueErrorevent_shape	base_distreinterpreted_batch_ndimssuper__init__)selfbase_distributionr   r
   shape	event_dimr   r   	__class__ ]/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/torch/distributions/independent.pyr   -   s   zIndependent.__init__c                    s`   |  t|}t|}| j|| jd | j  |_| j|_tt|j	|| jdd | j
|_
|S )NFr	   )_get_checked_instancer   torchSizer   expandr   r   r   r   _validate_args)r   r   	_instancenewr   r   r   r   =   s   

zIndependent.expandc                 C      | j jS N)r   has_rsampler   r   r   r   r$   J      zIndependent.has_rsamplec                 C   s   | j dkrdS | jjS )Nr   F)r   r   has_enumerate_supportr%   r   r   r   r'   N   s   
z!Independent.has_enumerate_supportc                 C   s    | j j}| jrt|| j}|S r#   )r   supportr   r   independent)r   resultr   r   r   r(   T   s   zIndependent.supportc                 C   r"   r#   )r   meanr%   r   r   r   r+   [   r&   zIndependent.meanc                 C   r"   r#   )r   moder%   r   r   r   r,   _   r&   zIndependent.modec                 C   r"   r#   )r   variancer%   r   r   r   r-   c   r&   zIndependent.variancec                 C      | j |S r#   )r   sampler   sample_shaper   r   r   r/   g      zIndependent.sampler1   returnc                 C   r.   r#   )r   rsampler0   r   r   r   r4   j   r2   zIndependent.rsamplec                 C   s   | j |}t|| jS r#   )r   log_probr   r   )r   valuer5   r   r   r   r5   m   s   zIndependent.log_probc                 C   s   | j  }t|| jS r#   )r   entropyr   r   )r   r7   r   r   r   r7   q   s   
zIndependent.entropyTc                 C   s    | j dkr	td| jj|dS )Nr   z5Enumeration over cartesian product is not implemented)r   )r   NotImplementedErrorr   enumerate_support)r   r   r   r   r   r9   u   s
   
zIndependent.enumerate_supportc                 C   s   | j jd| j d| j d S )N(z, ))r   __name__r   r   r%   r   r   r   __repr__|   s   zIndependent.__repr__r#   )T)r<   
__module____qualname____doc__r   r   strr   
Constraint__annotations__r   r   propertyr$   r'   dependent_propertyr(   r+   r,   r-   r   r   r/   r   Tensorr4   r5   r7   r9   r=   __classcell__r   r   r   r   r      s0   
 






)typingr   r   torch.distributionsr    torch.distributions.distributionr   torch.distributions.utilsr   torch.typesr   __all__r   r   r   r   r   <module>   s   