§ 昺h¾ãóh—ddlmZmZddlmZmZddlmZmZddlm Z Gd„dej ¦«Z dS) é)ÚnnÚTensor)ÚIterableÚDicté)ÚBatchHardTripletLossÚ$BatchHardTripletLossDistanceFunction)ÚSentenceTransformercón‡—eZdZdZejdfdedefˆfd„ Zde e e e fde fd„Z d „ZˆxZS) ÚBatchAllTripletLossa­ BatchAllTripletLoss takes a batch with (label, sentence) 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. You train dataset must contain at least 2 examples per label class. | 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 :param model: SentenceTransformer model :param distance_metric: Function that returns a distance between two emeddings. The class SiameseDistanceMetric contains pre-defined metrices that can be used :param margin: Negative samples should be at least margin further apart from the anchor than the positive. Example:: from sentence_transformers import SentenceTransformer, SentencesDataset, losses from sentence_transformers.readers import InputExample model = SentenceTransformer('distilbert-base-nli-mean-tokens') train_examples = [InputExample(texts=['Sentence from class 0'], label=0), InputExample(texts=['Another sentence from class 0'], label=0), InputExample(texts=['Sentence from class 1'], label=1), InputExample(texts=['Sentence from class 2'], label=2)] train_dataset = SentencesDataset(train_examples, model) train_dataloader = DataLoader(train_dataset, shuffle=True, batch_size=train_batch_size) train_loss = losses.BatchAllTripletLoss(model=model) éÚmodelÚmarginc󀕗tt|¦« ¦«||_||_||_dS)N)Úsuperr Ú__init__Úsentence_embedderÚtriplet_marginÚdistance_metric)ÚselfrrrÚ __class__s €úx/var/www/html/services/rag-service/venv/lib/python3.11/site-packages/sentence_transformers/losses/BatchAllTripletLoss.pyrzBatchAllTripletLoss.__init__#s@ø€õ Õ! 4Ñ(Ô(×1Ò1Ñ3Ô3Ð3Ø!&ˆÔØ$ˆÔØ.ˆÔÐÐóÚsentence_featuresÚlabelscóp—| |d¦«d}| ||¦«S)NrÚsentence_embedding)rÚbatch_all_triplet_loss)rrrÚreps rÚforwardzBatchAllTripletLoss.forward.s7€Ø×$Ò$Ð%6°qÔ%9Ñ:Ô:Ð;OÔPˆØ×*Ò*¨6°3Ñ7Ô7Ð7rcó|—| |¦«}| 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 érrg¼‰Ø—²Òœ<)rÚ unsqueezerrÚget_triplet_maskÚfloatÚsizeÚsum) rrÚ embeddingsÚ pairwise_distÚanchor_positive_distÚanchor_negative_distÚ triplet_lossÚmaskÚvalid_tripletsÚnum_positive_tripletss rrz*BatchAllTripletLoss.batch_all_triplet_loss2sÒ€ð×,Ò,¨ZÑ8Ô8ˆ à,×6Ò6°qÑ9Ô9ÐØ,×6Ò6°qÑ9Ô9Ðð ,Ð.BÑBÀTÔEXÑXˆ õ$Ô4°VÑ<Ô<ˆØ—z’z‘|”| lÑ2ˆ ð*+ˆ \ AÒ%Ñ&ð& l°UÒ&:Ô;ˆØ .× 3Ò 3°AÑ 6Ô 6Ðð $×'Ò'Ñ)Ô)Ð-BÀUÑ-JÑKˆ àÐr)Ú__name__Ú __module__Ú __qualname__Ú__doc__r Úeucledian_distancer r%rrrÚstrrr rÚ __classcell__)rs@rr r s¨ø€€€€€ððð<=ÔOØð /ð /à"ð /ðð /ð /ð /ð /ð /ð /ð8¨°$°s¸F°{Ô2CÔ)Dð8Èfð8ð8ð8ð8ð)ð)ð)ð)ð)ð)ð)rr N) ÚtorchrrÚtypingrrrr Ú)sentence_transformers.SentenceTransformerr ÚModuler ©rrúr<sŸðØÐÐÐÐÐÐÐØ!Ð!Ð!Ð!Ð!Ð!Ð!Ð!Ø\Ð\Ð\Ð\Ð\Ð\Ð\Ð\ØIÐIÐIÐIÐIÐIðTðTðTðTðT˜"œ)ñTôTðTðTðTr