§
    ’©ºj«  ã                   óÊ   — d dl mZ d dlZd dlmZ d dlmZ d dlmZmZ d dl	m
Z
 	 ddedee         d	ee         d
efd„Z	 	 	 ddedee         ded         d	ee         d
ef
d„ZdS )é    )ÚOptionalN)ÚTensor)ÚLiteral)Ú_check_inputÚ_reduce_distance_matrix)Ú_safe_matmulÚxÚyÚzero_diagonalÚreturnc                 ó:  — t          | ||¦  «        \  } }}t          j        | dd¬¦  «        }| |                     d¦  «        z  } t          j        |dd¬¦  «        }||                     d¦  «        z  }t	          | |¦  «        }|r|                     d¦  «         |S )zêCalculate the pairwise cosine similarity matrix.

    Args:
        x: tensor of shape ``[N,d]``
        y: tensor of shape ``[M,d]``
        zero_diagonal: determines if the diagonal of the distance matrix should be set to zero

    é   é   )ÚpÚdimr   )r   ÚtorchÚnormÚ	unsqueezer   Úfill_diagonal_)r	   r
   r   r   Údistances        úw/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/torchmetrics/functional/pairwise/cosine.pyÚ"_pairwise_cosine_similarity_updater      s¤   € õ ' q¨!¨]Ñ;Ô;Ñ€A€qˆ-åŒ:�a˜1 !Ð$Ñ$Ô$€DØ	ˆD�NŠN˜1ÑÔÑ€AÝŒ:�a˜1 !Ð$Ñ$Ô$€DØ	ˆD�NŠN˜1ÑÔÑ€Aå˜A˜qÑ!Ô!€HØð #Ø×Ò Ñ"Ô"Ð"Ø€Oó    Ú	reduction)ÚmeanÚsumÚnoneNc                 óD   — t          | ||¦  «        }t          ||¦  «        S )an  Calculate pairwise cosine similarity.

    .. math::
        s_{cos}(x,y) = \frac{<x,y>}{||x|| \cdot ||y||}
                     = \frac{\sum_{d=1}^D x_d \cdot y_d }{\sqrt{\sum_{d=1}^D x_i^2} \cdot \sqrt{\sum_{d=1}^D y_i^2}}

    If both :math:`x` and :math:`y` are passed in, the calculation will be performed pairwise
    between the rows of :math:`x` and :math:`y`.
    If only :math:`x` is passed in, the calculation will be performed between the rows of :math:`x`.

    Args:
        x: Tensor with shape ``[N, d]``
        y: Tensor with shape ``[M, d]``, optional
        reduction: reduction to apply along the last dimension. Choose between `'mean'`, `'sum'`
            (applied along column dimension) or  `'none'`, `None` for no reduction
        zero_diagonal: if the diagonal of the distance matrix should be set to 0. If only :math:`x` is given
            this defaults to ``True`` else if :math:`y` is also given it defaults to ``False``

    Returns:
        A ``[N,N]`` matrix of distances if only ``x`` is given, else a ``[N,M]`` matrix

    Example:
        >>> import torch
        >>> from torchmetrics.functional.pairwise import pairwise_cosine_similarity
        >>> x = torch.tensor([[2, 3], [3, 5], [5, 8]], dtype=torch.float32)
        >>> y = torch.tensor([[1, 0], [2, 1]], dtype=torch.float32)
        >>> pairwise_cosine_similarity(x, y)
        tensor([[0.5547, 0.8682],
                [0.5145, 0.8437],
                [0.5300, 0.8533]])
        >>> pairwise_cosine_similarity(x)
        tensor([[0.0000, 0.9989, 0.9996],
                [0.9989, 0.0000, 0.9998],
                [0.9996, 0.9998, 0.0000]])

    )r   r   )r	   r
   r   r   r   s        r   Úpairwise_cosine_similarityr   0   s&   € õT 2°!°Q¸ÑFÔF€HÝ" 8¨YÑ7Ô7Ð7r   )NN)NNN)Útypingr   r   r   Útyping_extensionsr   Ú(torchmetrics.functional.pairwise.helpersr   r   Útorchmetrics.utilities.computer   Úboolr   r   © r   r   ú<module>r&      s$  ðð Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð Ø %Ð %Ð %Ð %Ð %Ð %à ZÐ ZÐ ZÐ ZÐ ZÐ ZÐ ZÐ ZØ 7Ð 7Ð 7Ð 7Ð 7Ð 7ð LPðð ØðØ˜6Ô"ðØ:BÀ4¼.ðàðð ð ð ð4 Ø6:Ø$(ð	+8ð +8Øð+8à�Ôð+8ð Ð2Ô3ð+8ð ˜D”>ð	+8ð
 ð+8ð +8ð +8ð +8ð +8ð +8r   