ёitSSKJr SSKJr SSKJrJr SSKJr SSK J r \(aSSK r /r "S S \ 5rg) ) annotations) TYPE_CHECKING)param_one_aliasparam_two_alias) functional)LayerNc^\rSrSrSr\"SS/5SSU4Sjjj5r\"SS/SS /5SS j5rSS jr \ SS j5r \ RSS j5r \ SSj5r \ RSSj5r SrU=r$)PairwiseDistancea It computes the pairwise distance between two vectors. The distance is calculated by p-order norm: .. math:: \Vert x \Vert _p = \left( \sum_{i=1}^n \vert x_i \vert ^ p \right) ^ {1/p}. Parameters: p (float, optional): The order of norm. Default: :math:`2.0`. epsilon (float, optional): Add small value to avoid division by zero. Default: :math:`1e-6`. keepdim (bool, optional): Whether to reserve the reduced dimension in the output Tensor. The result tensor is one dimension less than the result of ``|x-y|`` unless :attr:`keepdim` is True. Default: False. name (str, optional): For details, please refer to :ref:`api_guide_Name`. Generally, no setting is required. Default: None. Shape: - x: :math:`[N, D]` or :math:`[D]`, where :math:`N` is batch size, :math:`D` is the dimension of the data. Available data type is float16, float32, float64. - y: :math:`[N, D]` or :math:`[D]`, y have the same dtype as x. - output: The same dtype as input tensor. - If :attr:`keepdim` is True, the output shape is :math:`[N, 1]` or :math:`[1]`, depending on whether the input has data shaped as :math:`[N, D]`. - If :attr:`keepdim` is False, the output shape is :math:`[N]` or :math:`[]`, depending on whether the input has data shaped as :math:`[N, D]`. Examples: .. code-block:: python >>> import paddle >>> x = paddle.to_tensor([[1., 3.], [3., 5.]], dtype=paddle.float64) >>> y = paddle.to_tensor([[5., 6.], [7., 8.]], dtype=paddle.float64) >>> dist = paddle.nn.PairwiseDistance() >>> distance = dist(x, y) >>> print(distance) Tensor(shape=[2], dtype=float64, place=Place(cpu), stop_gradient=True, [4.99999860, 4.99999860]) epsilonepscR>[TU]5 XlX lX0lX@lgN)super__init__prkeepdimname)selfrrrr __class__s X/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/nn/layer/distance.pyrPairwiseDistance.__init__Is$    xx1yx2c[R"XURURURUR 5$r)Fpairwise_distancerrrr)rrrs rforwardPairwiseDistance.forwardWs0"" $&&$,, dii  rcSnURS:waUS- nURSLaUS- nURbUS- nUR"S0URD6$)Nzp={p}ư>z, epsilon={epsilon}Fz, keepdim={keepdim}z , name={name})rrrformat__dict__)rmain_strs r extra_reprPairwiseDistance.extra_repr]s_ <<4  - -H <rOs/# I WuWr