sihddlmZmZddlmZmZddlmZddlmZm Z Gddej Z dS) )DictIterable)Tensornn)SentenceTransformer)BatchHardTripletLoss$BatchHardTripletLossDistanceFunctionceZdZejdfdededdffd Zdee e e fde de fd Z de d e de fd Z ede fd ZxZS) BatchAllTripletLossmodelmarginreturnNctt|||_||_||_dS)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. 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. Inputs: +------------------+--------+ | Texts | Labels | +==================+========+ | single sentences | class | +------------------+--------+ 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)superr __init__sentence_embeddertriplet_margindistance_metric)selfrrr __class__s c/var/www/icac/venv/lib/python3.11/site-packages/sentence_transformers/losses/BatchAllTripletLoss.pyrzBatchAllTripletLoss.__init__ sAL !4((11333!&$.sentence_featureslabelscp||dd}|||S)Nrsentence_embedding)rbatch_all_triplet_loss)rrrreps rforwardzBatchAllTripletLoss.forwardVs7$$%6q%9::;OP**63777r embeddingsc|||}|d}|d}||z |jz}tj|}||z}d||dk<||dk}|d} || 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) rrr" pairwise_distanchor_positive_distanchor_negative_dist triplet_lossmaskvalid_tripletsnum_positive_tripletss rrz*BatchAllTripletLoss.batch_all_triplet_lossZs,,Z88 ,66q99,66q99 ,.BBTEXX $4V<<zz||l2 *+ \A%&&lU&:; . 3 3A 6 6 $''))-BU-JK rcdS)Na @misc{hermans2017defense, title={In Defense of the Triplet Loss for Person Re-Identification}, author={Alexander Hermans and Lucas Beyer and Bastian Leibe}, year={2017}, eprint={1703.07737}, archivePrefix={arXiv}, primaryClass={cs.CV} } )rs rcitationzBatchAllTripletLoss.citations   r)__name__ __module__ __qualname__r eucledian_distancerr'rrrstrrr!rpropertyr3 __classcell__)rs@rr r s=O I/I/"I/ I/  I/I/I/I/I/I/V8$sF{2C)D8f8Y_8888)V))F))))V #   X     rr N) typingrrtorchrr)sentence_transformers.SentenceTransformerrr r Moduler r2rrr?s!!!!!!!!IIIIII\\\\\\\\FFFFF")FFFFFr