
    +sgp                        d dl mZ d dlmZ d dlmZ d dlmZ d dlm	c m
Z d dlmZm	Z	 d dlmZ  G d d	e      Z G d
 de	j"                        Zy)    )annotations)Iterable)Enum)AnyN)Tensornn)SentenceTransformerc                  "    e Zd ZdZd Zd Zd Zy)SiameseDistanceMetricz#The metric for the contrastive lossc                2    t        j                  | |d      S )N   pFpairwise_distancexys     _/var/www/html/venv/lib/python3.12/site-packages/sentence_transformers/losses/ContrastiveLoss.py<lambda>zSiameseDistanceMetric.<lambda>       Q00A;     c                2    t        j                  | |d      S )N   r   r   r   s     r   r   zSiameseDistanceMetric.<lambda>   r   r   c                4    dt        j                  | |      z
  S )Nr   )r   cosine_similarityr   s     r   r   zSiameseDistanceMetric.<lambda>   s    1q':':1a'@#@ r   N)__name__
__module____qualname____doc__	EUCLIDEAN	MANHATTANCOSINE_DISTANCE r   r   r   r      s    -;I;I@Or   r   c                  l     e Zd Zej                  ddf	 	 	 	 	 	 	 d fdZddZd	dZed
d       Z	 xZ
S )ContrastiveLoss      ?Tc                Z    t         |           || _        || _        || _        || _        y)a	  
        Contrastive loss. Expects as input two texts and a label of either 0 or 1. If the label == 1, then the distance between the
        two embeddings is reduced. If the label == 0, then the distance between the embeddings is increased.

        Args:
            model: SentenceTransformer model
            distance_metric: Function that returns a distance between
                two embeddings. The class SiameseDistanceMetric contains
                pre-defined metrices that can be used
            margin: Negative samples (label == 0) should have a distance
                of at least the margin value.
            size_average: Average by the size of the mini-batch.

        References:
            * Further information: http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf
            * `Training Examples > Quora Duplicate Questions <../../examples/training/quora_duplicate_questions/README.html>`_

        Requirements:
            1. (anchor, positive/negative) pairs

        Inputs:
            +-----------------------------------------------+------------------------------+
            | Texts                                         | Labels                       |
            +===============================================+==============================+
            | (anchor, positive/negative) pairs             | 1 if positive, 0 if negative |
            +-----------------------------------------------+------------------------------+

        Relations:
            - :class:`OnlineContrastiveLoss` is similar, but uses hard positive and hard negative pairs.
            It often yields better results.

        Example:
            ::

                from sentence_transformers import SentenceTransformer, SentenceTransformerTrainer, losses
                from datasets import Dataset

                model = SentenceTransformer("microsoft/mpnet-base")
                train_dataset = Dataset.from_dict({
                    "sentence1": ["It's nice weather outside today.", "He drove to work."],
                    "sentence2": ["It's so sunny.", "She walked to the store."],
                    "label": [1, 0],
                })
                loss = losses.ContrastiveLoss(model)

                trainer = SentenceTransformerTrainer(
                    model=model,
                    train_dataset=train_dataset,
                    loss=loss,
                )
                trainer.train()
        N)super__init__distance_metricmarginmodelsize_average)selfr.   r,   r-   r/   	__class__s        r   r+   zContrastiveLoss.__init__   s/    v 	.
(r   c                    | j                   j                  }t        t              j	                         D ]  \  }}|| j                   k(  sd| } n || j
                  | j                  dS )NzSiameseDistanceMetric.)r,   r-   r/   )r,   r   varsr   itemsr-   r/   )r0   distance_metric_namenamevalues       r   get_config_dictzContrastiveLoss.get_config_dictW   sn    #33<< 56<<> 	KD%,,,)?v'F$	
 $84;;`d`q`qrrr   c                   |D cg c]  }| j                  |      d    }}t        |      dk(  sJ |\  }}| j                  ||      }d|j                         |j	                  d      z  d|z
  j                         t        j                  | j                  |z
        j	                  d      z  z   z  }| j                  r|j                         S |j                         S c c}w )Nsentence_embeddingr   r(   r   )r.   lenr,   floatpowr   relur-   r/   meansum)	r0   sentence_featureslabelssentence_featurereps
rep_anchor	rep_other	distanceslossess	            r   forwardzContrastiveLoss.forward`   s    [lmGW

+,-ABmm4yA~~ $
I((Y?	LLNY]]1--V0B0B0Dqvvdkk\eNeGfGjGjklGm0mm
 !% 1 1v{{}Cvzz|C ns   C c                     y)Na~  
@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}
r%   )r0   s    r   citationzContrastiveLoss.citationj   s    r   )r.   r	   r-   r<   r/   boolreturnNone)rM   zdict[str, Any])rA   zIterable[dict[str, Tensor]]rB   r   rM   r   )rM   str)r   r   r    r   r$   r+   r8   rI   propertyrK   __classcell__)r1   s   @r   r'   r'      s`     .==!?)"?) 	?)
 ?) 
?)BsD  r   r'   )
__future__r   collections.abcr   enumr   typingr   torch.nn.functionalr   
functionalr   torchr   )sentence_transformers.SentenceTransformerr	   r   Moduler'   r%   r   r   <module>r[      s=    " $      IAD Abbii br   