o sh@sTddlmZmZddlZddlmZddlmZddlmZmZGdddeZ dS) )DictIterableN)Tensor)SentenceTransformer)BatchHardTripletLoss$BatchHardTripletLossDistanceFunctioncsveZdZejfdeddffdd Zdeee e fde de fdd Z de d e de fd d Z e de fd dZZS)BatchHardSoftMarginTripletLossmodelreturnNcs tt||||_||_dS)a BatchHardSoftMarginTripletLoss 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. This soft-margin variant does not require setting a margin. 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. 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 hard positives and negatives. Relations: * :class:`BatchHardTripletLoss` uses a user-specified margin, while this loss does not require setting a margin. 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.BatchHardSoftMarginTripletLoss(model) trainer = SentenceTransformerTrainer( model=model, train_dataset=train_dataset, loss=loss, ) trainer.train() N)superr __init__sentence_embedderdistance_metric)selfr r __class__y/var/www/html/alpaca_bot/venv/lib/python3.10/site-packages/sentence_transformers/losses/BatchHardSoftMarginTripletLoss.pyr sF z'BatchHardSoftMarginTripletLoss.__init__sentence_featureslabelscCs||dd}|||S)Nrsentence_embedding)r#batch_hard_triplet_soft_margin_loss)rrrreprrrforwardVs z&BatchHardSoftMarginTripletLoss.forward embeddingscCs||}t|}||}|jddd\}}t|}|jddd\} }|| d|} | jddd\} }tt || } | } | S)a6Build the triplet loss over a batch of embeddings. For each anchor, we get the hardest positive and hardest negative to form a triplet. Args: labels: labels of the batch, of size (batch_size,) embeddings: tensor of shape (batch_size, embed_dim) 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 rT)keepdimg?) rr get_anchor_positive_triplet_maskfloatmax get_anchor_negative_triplet_maskmintorchlog1pexpmean)rrr pairwise_distmask_anchor_positiveanchor_positive_disthardest_positive_dist_mask_anchor_negativemax_anchor_negative_distanchor_negative_disthardest_negative_disttl triplet_lossrrrr\s zBBatchHardSoftMarginTripletLoss.batch_hard_triplet_soft_margin_losscCsdS)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} } r)rrrrcitationsz'BatchHardSoftMarginTripletLoss.citation)__name__ __module__ __qualname__reucledian_distancerr rrstrrrrpropertyr1 __classcell__rrrrr s"J+r ) typingrrr"r)sentence_transformers.SentenceTransformerrrrr rrrrs