+
    &j,                     d    ^ RI Hu Ht ^ RIHt ^RIHt RR.t ! R R]4      t	 ! R R]4      t
R# )    NTensor)ModulePairwiseDistanceCosineSimilarityc                   l   a a ] tR t^
t oRt. ROtR	V3R lV 3R llltV3R lR ltV3R ltRt	Vt
V ;t# )
r   a  
Computes the pairwise distance between input vectors, or between columns of input matrices.

Distances are computed using ``p``-norm, with constant ``eps`` added to avoid division by zero
if ``p`` is negative, i.e.:

.. math ::
    \mathrm{dist}\left(x, y\right) = \left\Vert x-y + \epsilon e \right\Vert_p,

where :math:`e` is the vector of ones and the ``p``-norm is given by.

.. math ::
    \Vert x \Vert _p = \left( \sum_{i=1}^n  \vert x_i \vert ^ p \right) ^ {1/p}.

Args:
    p (real, optional): the norm degree. Can be negative. Default: 2
    eps (float, optional): Small value to avoid division by zero.
        Default: 1e-6
    keepdim (bool, optional): Determines whether or not to keep the vector dimension.
        Default: False
Shape:
    - Input1: :math:`(N, D)` or :math:`(D)` where `N = batch dimension` and `D = vector dimension`
    - Input2: :math:`(N, D)` or :math:`(D)`, same shape as the Input1
    - Output: :math:`(N)` or :math:`()` based on input dimension.
      If :attr:`keepdim` is ``True``, then :math:`(N, 1)` or :math:`(1)` based on input dimension.

Examples:
    >>> pdist = nn.PairwiseDistance(p=2)
    >>> input1 = torch.randn(100, 128)
    >>> input2 = torch.randn(100, 128)
    >>> output = pdist(input1, input2)
c                0   < V ^8  d   QhRS[ RS[ RS[RR/# )   pepskeepdimreturnNfloatbool)format__classdict__s   "q/Users/jameslopez/projects/CWCArchive/cwc-podcast/.venv/lib/python3.14/site-packages/torch/nn/modules/distance.py__annotate__PairwiseDistance.__annotate__1   s-      #(:>	    c                H   < \         SV `  4        Wn        W n        W0n        R # N)super__init__normr   r   )selfr   r   r   	__class__s   &&&&r   r   PairwiseDistance.__init__1   s     		r   c                ,   < V ^8  d   QhRS[ RS[ RS[ /# r
   x1x2r   r   )r   r   s   "r   r   r   9   s'     N N& Nf N Nr   c                p    \         P                  ! WV P                  V P                  V P                  4      # z
Runs the forward pass.
)Fpairwise_distancer   r   r   r   r"   r#   s   &&&r   forwardPairwiseDistance.forward9   s'     ""2499dhhMMr   c                >   < V ^8  d   Qh/ S[ ;R&   S[ ;R&   S[;R&   # )r
   r   r   r   r   )r   r   s   "r   r   r   
   s/     F KG H 
JI J MK r   )r   r   r   )r   r   r   )g       @gư>F__name__
__module____qualname____firstlineno____doc____constants__r   r)   __annotate_func____static_attributes____classdictcell____classcell__r   r   s   @@r   r   r   
   s0     B /M
 N N_  r   c                   l   a a ] tR t^@t oRtRR.tR
V3R lV 3R llltV3R lR ltV3R ltR	t	Vt
V ;t# )r   aK  Returns cosine similarity between :math:`x_1` and :math:`x_2`, computed along `dim`.

.. math ::
    \text{similarity} = \dfrac{x_1 \cdot x_2}{\max(\Vert x_1 \Vert _2 \cdot \Vert x_2 \Vert _2, \epsilon)}.

Args:
    dim (int, optional): Dimension where cosine similarity is computed. Default: 1
    eps (float, optional): Small value to avoid division by zero.
        Default: 1e-8
Shape:
    - Input1: :math:`(\ast_1, D, \ast_2)` where D is at position `dim`
    - Input2: :math:`(\ast_1, D, \ast_2)`, same number of dimensions as x1, matching x1 size at dimension `dim`,
      and broadcastable with x1 at other dimensions.
    - Output: :math:`(\ast_1, \ast_2)`

Examples:
    >>> input1 = torch.randn(100, 128)
    >>> input2 = torch.randn(100, 128)
    >>> cos = nn.CosineSimilarity(dim=1, eps=1e-6)
    >>> output = cos(input1, input2)
dimr   c                *   < V ^8  d   QhRS[ RS[RR/# )r
   r9   r   r   Nintr   )r   r   s   "r   r   CosineSimilarity.__annotate__[   s"      C % 4 r   c                <   < \         SV `  4        Wn        W n        R # r   )r   r   r9   r   )r   r9   r   r   s   &&&r   r   CosineSimilarity.__init__[   s    r   c                ,   < V ^8  d   QhRS[ RS[ RS[ /# r!   r   )r   r   s   "r   r   r=   `   s"     ? ?& ?f ? ?r   c                Z    \         P                  ! WV P                  V P                  4      # r%   )r&   cosine_similarityr9   r   r(   s   &&&r   r)   CosineSimilarity.forward`   s!     ""2488TXX>>r   c                2   < V ^8  d   Qh/ S[ ;R&   S[;R&   # )r
   r9   r   r;   )r   r   s   "r   r   r=   @   s     0 
H1 2 
J3 r   )r9   r   )   g:0yE>r,   r7   s   @@r   r   r   @   s1     , ENM 
? ?A  r   )torch.nn.functionalnn
functionalr&   torchr   moduler   __all__r   r    r   r   <module>rM      s9        1
23Nv 3Nl$?v $?r   