3
I4W^�	  ã               @   s<   d dl mZ ddlmZ G dd„ deƒZG dd„ deƒZdS )	é   )ÚModuleé   )Ú
functionalc                   s4   e Zd ZdZdddgZd‡ fdd	„	Zd
d„ Z‡  ZS )ÚPairwiseDistanceau  
    Computes the batchwise pairwise distance between vectors :math:`v_1`, :math:`v_2` using the p-norm:

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

    Args:
        p (real): the norm degree. 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)` where `D = vector dimension`
        - Input2: :math:`(N, D)`, same shape as the Input1
        - Output: :math:`(N)`. If :attr:`keepdim` is ``True``, then :math:`(N, 1)`.
    Examples::
        >>> pdist = nn.PairwiseDistance(p=2)
        >>> input1 = torch.randn(100, 128)
        >>> input2 = torch.randn(100, 128)
        >>> output = pdist(input1, input2)
    ÚnormÚepsÚkeepdimç       @ç�íµ ÷Æ°>Fc                s$   t t| ƒjƒ  || _|| _|| _d S )N)Úsuperr   Ú__init__r   r   r   )ÚselfÚpr   r   )Ú	__class__© ú:/tmp/pip-build-e66j97b2/torch/torch/nn/modules/distance.pyr      s    zPairwiseDistance.__init__c             C   s   t j||| j| j| jƒS )N)ÚFZpairwise_distancer   r   r   )r   Úx1Úx2r   r   r   Úforward$   s    zPairwiseDistance.forward)r	   r
   F)Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú__constants__r   r   Ú__classcell__r   r   )r   r   r      s   
r   c                   s2   e Zd ZdZddgZd
‡ fdd„	Zdd	„ Z‡  ZS )ÚCosineSimilaritya'  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 shape as the Input1
        - 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)
    Údimr   r   ç:Œ0âŽyE>c                s   t t| ƒjƒ  || _|| _d S )N)r   r   r   r   r   )r   r   r   )r   r   r   r   >   s    zCosineSimilarity.__init__c             C   s   t j||| j| jƒS )N)r   Zcosine_similarityr   r   )r   r   r   r   r   r   r   C   s    zCosineSimilarity.forward)r   r   )r   r   r   r   r   r   r   r   r   r   )r   r   r   (   s   r   N)Úmoduler   Ú r   r   r   r   r   r   r   r   Ú<module>   s   #