Ch`!vSSKJr SSKJr SSKrSSKJrJr SSKJr SSK J r "SS \R5r g) ) annotations)IterableN)Tensornn)SentenceTransformer)$BatchHardTripletLossDistanceFunctionc^\rSrSr\R S4S U4SjjjrS SjrS Sjr\ S SSjj5r \ S SSjj5r \ SSj5r S rU=r$)BatchSemiHardTripletLoss cF>[TU]5 XlX0lX lg)a BatchSemiHardTripletLoss 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. It then looks for the semi hard positives and negatives. 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. Definitions: :Easy triplets: Triplets which have a loss of 0 because ``distance(anchor, positive) + margin < distance(anchor, negative)``. :Hard triplets: Triplets where the negative is closer to the anchor than the positive, i.e., ``distance(anchor, negative) < distance(anchor, positive)``. :Semi-hard triplets: Triplets where the negative is not closer to the anchor than the positive, but which still have a positive loss, i.e., ``distance(anchor, positive) < distance(anchor, negative) + margin``. 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. 3. Your dataset should contain semi hard positives and negatives. 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 only semi hard positive and negatives. * :class:`BatchAllTripletLoss` uses all possible, valid triplets, rather than only semi hard positive and negatives. * :class:`BatchHardSoftMarginTripletLoss` uses only the hardest positive and negative samples, rather than only semi hard positive and negatives. Also, it does not require setting a margin. 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.BatchSemiHardTripletLoss(model) trainer = SentenceTransformerTrainer( model=model, train_dataset=train_dataset, loss=loss, ) trainer.train() N)super__init__sentence_embeddermargindistance_metric)selfmodelrr __class__s m/var/www/html/shao/venv/lib/python3.13/site-packages/sentence_transformers/losses/BatchSemiHardTripletLoss.pyr!BatchSemiHardTripletLoss.__init__s"f !& .cRURUS5SnURX#5$)Nrsentence_embedding)rbatch_semi_hard_triplet_loss)rsentence_featureslabelsreps rforward BatchSemiHardTripletLoss.forwardfs/$$%6q%9:;OP00==rc dURS5nURU5nXR5:HnU)n[R"U5nUR US/5nUR US/5U[R "UR5SS/5:-n[R "[R"USSS9S:Xf/5n U R5n [R "[RXx5Xf/5n U R5n [RX55n U R SU/5n [R"XU 5n X<- UR-n UR5RUR5[R "XaRS9- nURUR5n[R"U5n[R"[R""X-[R$"S/URS955U- nU$)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 rTkeepdimsg)device) unsqueezerttorchnumelrepeatreshapesumr _masked_minimum_masked_maximumwhererfloattor&eyemaxtensor)rr embeddings pdist_matrix adjacency adjacency_not batch_sizepdist_matrix_tilemask mask_finalnegatives_outsidenegatives_insidesemi_hard_negativesloss_matmask_positives num_positives triplet_losss rr5BatchSemiHardTripletLoss.batch_semi_hard_triplet_lossms!!!$++J7 hhj( " [[( (//Q@##ZO48IEMMZfZhZhZjmoqrlsLt8tu]]599T1t#Ds#JZLde \\^ !MM $ 4 45F MPZOg .//13CCL`+22Az?C#kk*IYZ 6$++E"*--fmm/b  rr ) __future__rcollections.abcrr)rr)sentence_transformers.SentenceTransformerrBatchHardTripletLossr Moduler rUrrrjs)"$ IFnryynr