l^(h|rddlmZddlmZddlmZmZddlmZddl m Z m Z GddejZ y ) ) annotations)Iterable)Tensornn)SentenceTransformer)BatchHardTripletLoss$BatchHardTripletLossDistanceFunctioncfeZdZejdf dfd ZddZddZed dZ xZ S) BatchAllTripletLosscLt|||_||_||_y)a BatchAllTripletLoss takes a batch with (sentence, label) pairs and computes the loss for all possible, valid triplets, i.e., anchor and positive must have the same label, anchor and negative a different label. The labels must be integers, with same label indicating sentences from the same class. Your train dataset must contain at least 2 examples per label class. Args: model: SentenceTransformer model distance_metric: Function that returns a distance between two embeddings. The class SiameseDistanceMetric contains pre-defined metrics that can be used. margin: Negative samples should be at least margin further apart from the anchor than the positive. References: * Source: https://github.com/NegatioN/OnlineMiningTripletLoss/blob/master/online_triplet_loss/losses.py * Paper: In Defense of the Triplet Loss for Person Re-Identification, https://arxiv.org/abs/1703.07737 * Blog post: https://omoindrot.github.io/triplet-loss Requirements: 1. Each sentence must be labeled with a class. 2. Your dataset must contain at least 2 examples per labels class. Inputs: +------------------+--------+ | Texts | Labels | +==================+========+ | single sentences | class | +------------------+--------+ Recommendations: - Use ``BatchSamplers.GROUP_BY_LABEL`` (:class:`docs `) to ensure that each batch contains 2+ examples per label class. Relations: * :class:`BatchHardTripletLoss` uses only the hardest positive and negative samples, rather than all possible, valid triplets. * :class:`BatchHardSoftMarginTripletLoss` uses only the hardest positive and negative samples, rather than all possible, valid triplets. Also, it does not require setting a margin. * :class:`BatchSemiHardTripletLoss` uses only semi-hard triplets, valid triplets, rather than all possible, valid triplets. Example: :: from sentence_transformers import SentenceTransformer, SentenceTransformerTrainer, losses from datasets import Dataset model = SentenceTransformer("microsoft/mpnet-base") # E.g. 0: sports, 1: economy, 2: politics train_dataset = Dataset.from_dict({ "sentence": [ "He played a great game.", "The stock is up 20%", "They won 2-1.", "The last goal was amazing.", "They all voted against the bill.", ], "label": [0, 1, 0, 0, 2], }) loss = losses.BatchAllTripletLoss(model) trainer = SentenceTransformerTrainer( model=model, train_dataset=train_dataset, loss=loss, ) trainer.train() N)super__init__sentence_embeddertriplet_margindistance_metric)selfmodelrmargin __class__s n/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/sentence_transformers/losses/BatchAllTripletLoss.pyrzBatchAllTripletLoss.__init__ s)T !&$.cT|j|dd}|j||S)Nrsentence_embedding)rbatch_all_triplet_loss)rsentence_featureslabelsreps rforwardzBatchAllTripletLoss.forward\s1$$%6q%9:;OP**6377rcN|j|}|jd}|jd}||z |jz}tj|}|j |z}d||dk<||dkD}|j d} |j| dzz }|S)a]Build the triplet loss over a batch of embeddings. We generate all the valid triplets and average the loss over the positive ones. Args: labels: labels of the batch, of size (batch_size,) embeddings: tensor of shape (batch_size, embed_dim) margin: margin for triplet loss squared: Boolean. If true, output is the pairwise squared euclidean distance matrix. If false, output is the pairwise euclidean distance matrix. Returns: Label_Sentence_Triplet: scalar tensor containing the triplet loss rrgؗҜ<)r unsqueezerr get_triplet_maskfloatsizesum) rr embeddings pairwise_distanchor_positive_distanchor_negative_dist triplet_lossmaskvalid_tripletsnum_positive_tripletss rrz*BatchAllTripletLoss.batch_all_triplet_loss`s,,Z8 ,66q9,66q9 ,.BBTEXEXX $44V<zz|l2 *+ \A%&&lU&:; . 3 3A 6 $'')-BU-JK rcy)Na @misc{hermans2017defense, title={In Defense of the Triplet Loss for Person Re-Identification}, author={Alexander Hermans and Lucas Beyer and Bastian Leibe}, year={2017}, eprint={1703.07737}, archivePrefix={arXiv}, primaryClass={cs.CV} } )rs rcitationzBatchAllTripletLoss.citations r)rrrr%returnNone)rzIterable[dict[str, Tensor]]rrr3r)rrr(rr3r)r3str) __name__ __module__ __qualname__r eucledian_distancerr rpropertyr2 __classcell__)rs@rr r sV=OO M/"M/ M/  M/^8)V  rr N) __future__rcollections.abcrtorchrr)sentence_transformers.SentenceTransformerrr r Moduler r1rrrAs&"$I\J"))Jr