o sÒhŠã@sRddlmZmZddlmZmZddlmZddlmZm Z Gdd„dej ƒZ dS) é)ÚDictÚIterable)ÚTensorÚnn)ÚSentenceTransformeré)ÚBatchHardTripletLossÚ$BatchHardTripletLossDistanceFunctioncs|eZdZejdfdededdf‡fdd„ Zdee e e fd e de fd d „Z d e d e de fd d„Z ede fdd„ƒZ‡ZS)ÚBatchAllTripletLosséÚmodelÚmarginÚreturnNcs$tt|ƒ ¡||_||_||_dS)aÇ 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)Úsuperr Ú__init__Úsentence_embedderÚtriplet_marginÚdistance_metric)Úselfr rr ©Ú __class__©ún/var/www/html/alpaca_bot/venv/lib/python3.10/site-packages/sentence_transformers/losses/BatchAllTripletLoss.pyr sF zBatchAllTripletLoss.__init__Úsentence_featuresÚlabelscCs| |d¡d}| ||¡S)NrÚsentence_embedding)rÚbatch_all_triplet_loss)rrrÚreprrrÚforwardVs zBatchAllTripletLoss.forwardÚ embeddingsc Csx| |¡}| d¡}| d¡}|||j}t |¡}| ¡|}d||dk<||dk}| d¡} | ¡| d}|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) rrrÚ pairwise_distÚanchor_positive_distÚanchor_negative_distÚ triplet_lossÚmaskÚvalid_tripletsÚnum_positive_tripletsrrrrZs       z*BatchAllTripletLoss.batch_all_triplet_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)rrrrÚcitation…szBatchAllTripletLoss.citation)Ú__name__Ú __module__Ú __qualname__r Úeucledian_distancerr#rrrÚstrrrrÚpropertyr-Ú __classcell__rrrrr süþüû"K+r N) ÚtypingrrÚtorchrrÚ)sentence_transformers.SentenceTransformerrrr ÚModuler rrrrÚs