JTh bSSKJs Jr SSKJr SSKJr SS/r"SS\5r "SS\5r g) N)Tensor)ModulePairwiseDistanceCosineSimilarityc ^\rSrSr%Sr/SQr\\S'\\S'\\S'SS\S\S\SS 4U4S jjjr S \ S \ S\ 4S jr Sr U=r $)r a Computes the pairwise distance between input vectors, or between columns of input matrices. Distances are computed using ``p``-norm, with constant ``eps`` added to avoid division by zero if ``p`` is negative, i.e.: .. math :: \mathrm{dist}\left(x, y\right) = \left\Vert x-y + \epsilon e \right\Vert_p, where :math:`e` is the vector of ones and the ``p``-norm is given by. .. math :: \Vert x \Vert _p = \left( \sum_{i=1}^n \vert x_i \vert ^ p \right) ^ {1/p}. Args: p (real, optional): the norm degree. Can be negative. Default: 2 eps (float, optional): Small value to avoid division by zero. Default: 1e-6 keepdim (bool, optional): Determines whether or not to keep the vector dimension. Default: False Shape: - Input1: :math:`(N, D)` or :math:`(D)` where `N = batch dimension` and `D = vector dimension` - Input2: :math:`(N, D)` or :math:`(D)`, same shape as the Input1 - Output: :math:`(N)` or :math:`()` based on input dimension. If :attr:`keepdim` is ``True``, then :math:`(N, 1)` or :math:`(1)` based on input dimension. Examples:: >>> pdist = nn.PairwiseDistance(p=2) >>> input1 = torch.randn(100, 128) >>> input2 = torch.randn(100, 128) >>> output = pdist(input1, input2) )normepskeepdimr r r preturnNcF>[TU]5 XlX lX0lgN)super__init__r r r )selfr r r __class__s Q/var/www/auris/envauris/lib/python3.13/site-packages/torch/nn/modules/distance.pyrPairwiseDistance.__init__1s   x1x2cp[R"XURURUR5$r)Fpairwise_distancer r r rrrs rforwardPairwiseDistance.forward9s%""2499dhh MMr)r r r )g@gư>F)__name__ __module__ __qualname____firstlineno____doc__ __constants__float__annotations__boolrrr__static_attributes__ __classcell__rs@rrr stB/M K J MBG#(:> N&NfNNNrct^\rSrSr%SrSS/r\\S'\\S'S S\S\SS4U4Sjjjr S\ S \ S\ 4S jr S r U=r $) r=aOReturns cosine similarity between :math:`x_1` and :math:`x_2`, computed along `dim`. .. math :: \text{similarity} = \dfrac{x_1 \cdot x_2}{\max(\Vert x_1 \Vert _2 \cdot \Vert x_2 \Vert _2, \epsilon)}. Args: dim (int, optional): Dimension where cosine similarity is computed. Default: 1 eps (float, optional): Small value to avoid division by zero. Default: 1e-8 Shape: - Input1: :math:`(\ast_1, D, \ast_2)` where D is at position `dim` - Input2: :math:`(\ast_1, D, \ast_2)`, same number of dimensions as x1, matching x1 size at dimension `dim`, and broadcastable with x1 at other dimensions. - Output: :math:`(\ast_1, \ast_2)` Examples:: >>> input1 = torch.randn(100, 128) >>> input2 = torch.randn(100, 128) >>> cos = nn.CosineSimilarity(dim=1, eps=1e-6) >>> output = cos(input1, input2) dimr rNc:>[TU]5 XlX lgr)rrr.r )rr.r rs rrCosineSimilarity.__init__Ws rrrcZ[R"XURUR5$r)rcosine_similarityr.r rs rrCosineSimilarity.forward\s""2488TXX>>r)r.r )rg:0yE>)r r!r"r#r$r%intr'r&rrrr)r*r+s@rrr=s[*ENM H JC%4 ?&?f???r) torch.nn.functionalnn functionalrtorchrmoduler__all__rrrrr<s9 1 20Nv0Nf ?v ?r