
    9j                     l    d dl Z d dl mZ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gZ G d de      Zy)	    N)nanTensor)constraints)Distribution)broadcast_all)_Number_sizeUniformc            	       @    e Zd ZdZdZed        Zedefd       Zedefd       Z	edefd       Z
edefd       Z	 dd
eez  deez  ded	z  dd	f fdZd fd	Z ej"                  dd      d        Z ej(                         fdedefdZd Zd Zd Zd Z xZS )r
   a  
    Generates uniformly distributed random samples from the half-open interval
    ``[low, high)``.

    Example::

        >>> m = Uniform(torch.tensor([0.0]), torch.tensor([5.0]))
        >>> m.sample()  # uniformly distributed in the range [0.0, 5.0)
        >>> # xdoctest: +SKIP
        tensor([ 2.3418])

    Args:
        low (float or Tensor): lower range (inclusive).
        high (float or Tensor): upper range (exclusive).
    Tc                     t        j                  | j                        t        j                  | j                        dS )N)lowhigh)r   	less_thanr   greater_thanr   selfs    [/media/conek/DATA/Code/OCR/venv/lib/python3.12/site-packages/torch/distributions/uniform.pyarg_constraintszUniform.arg_constraints!   s2     ((3,,TXX6
 	
    returnc                 :    | j                   | j                  z   dz  S )N   r   r   r   s    r   meanzUniform.mean)   s    		DHH$))r   c                 (    t         | j                  z  S N)r   r   r   s    r   modezUniform.mode-   s    TYYr   c                 :    | j                   | j                  z
  dz  S )NgLXz@r   r   s    r   stddevzUniform.stddev1   s    		DHH$//r   c                 X    | j                   | j                  z
  j                  d      dz  S )Nr      )r   r   powr   s    r   variancezUniform.variance5   s%    		DHH$))!,r11r   Nr   r   validate_argsc                     t        ||      \  | _        | _        t        |t              r%t        |t              rt        j                         }n| j                  j                         }t        | %  ||       y )Nr$   )
r   r   r   
isinstancer   torchSizesizesuper__init__)r   r   r   r$   batch_shape	__class__s        r   r,   zUniform.__init__9   sY     ,C6$)c7#
4(A**,K((--/KMBr   c                 *   | j                  t        |      }t        j                  |      }| j                  j                  |      |_        | j                  j                  |      |_        t        t        |#  |d       | j                  |_	        |S )NFr&   )
_get_checked_instancer
   r(   r)   r   expandr   r+   r,   _validate_args)r   r-   	_instancenewr.   s       r   r1   zUniform.expandG   st    (()<jj-((//+.99##K0gs$[$F!00
r   Fr   )is_discrete	event_dimc                 V    t        j                  | j                  | j                        S r   )r   intervalr   r   r   s    r   supportzUniform.supportP   s     ##DHHdii88r   sample_shapec                     | j                  |      }t        j                  || j                  j                  | j                  j
                        }| j                  || j                  | j                  z
  z  z   S )N)dtypedevice)_extended_shaper(   randr   r<   r=   r   )r   r:   shaper?   s       r   rsamplezUniform.rsampleU   sU    $$\2zz%txx~~dhhooNxx$$))dhh"6777r   c                    | j                   r| j                  |       | j                  j                  |      j	                  | j                        }| j
                  j                  |      j	                  | j                        }t        j                  |j                  |            t        j                  | j
                  | j                  z
        z
  S r   )
r2   _validate_sampler   letype_asr   gtr(   logmul)r   valuelbubs       r   log_probzUniform.log_probZ   s    !!%(XX[[''1YY\\% ((2yy$uyyTXX1E'FFFr   c                     | j                   r| j                  |       || j                  z
  | j                  | j                  z
  z  }|j	                  dd      S )Nr      )minmax)r2   rC   r   r   clampr   rI   results      r   cdfzUniform.cdfa   sL    !!%($(("tyy488';<||q|))r   c                 X    || j                   | j                  z
  z  | j                  z   }|S r   r   rR   s      r   icdfzUniform.icdfg   s'    $))dhh./$((:r   c                 Z    t        j                  | j                  | j                  z
        S r   )r(   rG   r   r   r   s    r   entropyzUniform.entropyk   s    yyTXX-..r   r   )__name__
__module____qualname____doc__has_rsamplepropertyr   r   r   r   r   r#   floatboolr,   r1   r   dependent_propertyr9   r(   r)   r	   rA   rL   rT   rV   rX   __classcell__)r.   s   @r   r
   r
      s,     K
 
 *f * * f   0 0 0 2& 2 2 &*	Ce^C unC d{	C
 
C $[##C9 D9 -7EJJL 8E 8V 8
G*/r   )r(   r   r   torch.distributionsr    torch.distributions.distributionr   torch.distributions.utilsr   torch.typesr   r	   __all__r
    r   r   <module>ri      s0      + 9 3 & +^/l ^/r   