Pipeline API

# Pipeline API 参考 ## 概述 Pipeline 提供了一种最简单的方式来使用预训练模型进行推理。它们封装了分词、模型加载和后处理，为数十种任务提供了统一的接口。 ## 基础用法 通过指定任务创建 pipeline： python from transformers import pipeline # 自动选择任务的默认模型 pipe = pipeline("text-classification") result = pipe("This is great!") 或者指定模型： python pipe = pipeline("text-classification", model="distilbert-base-uncased-finetuned-sst-2-english") ## 支持的任务 ### 自然语言处理 **text-generation**: 生成文本续写 python generator = pipeline("text-generation", model="gpt2") output = generator("Once upon a time", max_length=50, num_return_sequences=2) **text-classification**: 将文本分类到不同类别 python classifier = pipeline("text-classification") result = classifier("I love this product!") # 返回标签和分数 **token-classification**: 对单个 token 进行标注 (NER, POS 标注) python ner = pipeline("token-classification", model="dslim/bert-base-NER") entities = ner("Hugging Face is based in New York City") **question-answering**: 从上下文中提取答案 python qa = pipeline("question-answering") result = qa(question="What is the capital?", context="Paris is the capital of France.") **fill-mask**: 预测被掩码的 token python unmasker = pipeline("fill-mask", model="bert-base-uncased") result = unmasker("Paris is the [MASK] of France") **summarization**: 总结长文本 python summarizer = pipeline("summarization", model="facebook/bart-large-cnn") summary = summarizer("Long article text...", max_length=130, min_length=30) **translation**: 语言间翻译 python translator = pipeline("translation_en_to_fr", model="Helsinki-NLP/opus-mt-en-fr") result = translator("Hello, how are you?") **zero-shot-classification**: 无需训练数据进行分类 python classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli") result = classifier( "This is a course about Python programming", candidate_labels=["education", "politics", "business"] ) **sentiment-analysis**: text-classification 的别名，专注于情感分析 python sentiment = pipeline("sentiment-analysis") result = sentiment("This product exceeded my expectations!") ### 计算机视觉 **image-classification**: