o shH@shddlZddlmZmZmZmZmZddlZddlmZm Z ddl m Z e e ZGddde jZdS)N)CallableDictIterableTupleUnion)Tensornn)SentenceTransformercseZdZdddefdedededededed ed d ffd d Z de e e e fde d ee ee e fffddZed e fddZZS) SoftmaxLossTFmodelsentence_embedding_dimension num_labelsconcatenation_sent_repconcatenation_sent_difference!concatenation_sent_multiplicationloss_fctreturnNc stt|||_||_||_||_||_d}|r|d7}|r$|d7}|r*|d7}t d |t j ||||j d|_||_dS)a\ This loss was used in our SBERT publication (https://arxiv.org/abs/1908.10084) to train the SentenceTransformer model on NLI data. It adds a softmax classifier on top of the output of two transformer networks. :class:`MultipleNegativesRankingLoss` is an alternative loss function that often yields better results, as per https://arxiv.org/abs/2004.09813. Args: model (SentenceTransformer): The SentenceTransformer model. sentence_embedding_dimension (int): The dimension of the sentence embeddings. num_labels (int): The number of different labels. concatenation_sent_rep (bool): Whether to concatenate vectors u,v for the softmax classifier. Defaults to True. concatenation_sent_difference (bool): Whether to add abs(u-v) for the softmax classifier. Defaults to True. concatenation_sent_multiplication (bool): Whether to add u*v for the softmax classifier. Defaults to False. loss_fct (Callable): Custom pytorch loss function. If not set, uses nn.CrossEntropyLoss(). Defaults to nn.CrossEntropyLoss(). References: - Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks: https://arxiv.org/abs/1908.10084 - `Training Examples > Natural Language Inference <../../examples/training/nli/README.html>`_ Requirements: 1. sentence pairs with a class label Inputs: +---------------------------------------+--------+ | Texts | Labels | +=======================================+========+ | (sentence_A, sentence_B) pairs | class | +---------------------------------------+--------+ Example: :: from sentence_transformers import SentenceTransformer, SentenceTransformerTrainer, losses from datasets import Dataset model = SentenceTransformer("microsoft/mpnet-base") train_dataset = Dataset.from_dict({ "sentence1": [ "A person on a horse jumps over a broken down airplane.", "A person on a horse jumps over a broken down airplane.", "A person on a horse jumps over a broken down airplane.", "Children smiling and waving at camera", ], "sentence2": [ "A person is training his horse for a competition.", "A person is at a diner, ordering an omelette.", "A person is outdoors, on a horse.", "There are children present.", ], "label": [1, 2, 0, 0], }) loss = losses.SoftmaxLoss(model, model.get_sentence_embedding_dimension(), num_labels=3) trainer = SentenceTransformerTrainer( model=model, train_dataset=train_dataset, loss=loss, ) trainer.train() rz'Softmax loss: #Vectors concatenated: {})deviceN)superr __init__r r rrrloggerinfoformatrLinearr classifierr) selfr r r rrrrnum_vectors_concatenated __class__f/var/www/html/alpaca_bot/venv/lib/python3.10/site-packages/sentence_transformers/losses/SoftmaxLoss.pyr s$G  zSoftmaxLoss.__init__sentence_featureslabelsc sfdd|D}|\}}g}jr||||jr)|t||jr3|||t|d}|}|durM|| d} | S||fS)Ncsg|] }|dqS)sentence_embedding)r ).0sentence_featurerr!r" ksz'SoftmaxLoss.forward..r) rappendrtorchabsrcatrrview) rr#r$repsrep_arep_bvectors_concatfeaturesoutputlossr!r(r"forwardhs     zSoftmaxLoss.forwardcCsdS)Na @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } r!r(r!r!r"citationszSoftmaxLoss.citation)__name__ __module__ __qualname__rCrossEntropyLossr intboolrrrrstrrrrr7propertyr8 __classcell__r!r!rr"r s> [ r )loggingtypingrrrrrr,rr)sentence_transformers.SentenceTransformerr getLoggerr9rModuler r!r!r!r"s