虚拟环境文件夹\Lib\site-packages\transformers\pipelines\__init__.py

# 在SUPPORTED_TASKS对象中，每个字典元素的key值方NLP任务名称，每个字典元素的value值为该NLP任务的具体配置。
SUPPORTED_TASKS = {
    "audio-classification": {
        "impl": AudioClassificationPipeline, # 当前NLP任务的pipeline类接口
        "tf": (),# 指定TensorFloew框架下的自动类模型
        "pt": (AutoModelForAudioClassification,) if is_torch_available() else (), # 指定Pytorch框架下的自动类模型
        "default": {"model": {"pt": "superb/wav2vec2-base-superb-ks"}}, # 要加载的权重文件
        "type": "audio",
    },

# <task-name>代表任务字符串，如文本分类任务就是“sentiment--anaysis:
# <model name>:代表加载的模型：在手动加载模式下，<model name>可以是本地的预训练模型文件；在自动加载模式下，<model name>是预训练模型的唯一标识符。
pipeline("<task-name>",model="<model-name>")
pipeline('<task-name>',model='<model name>',tokenizer='<tokenizer_name>')

# 代码实现：完成文本分类任务
from transformers import *
nlp = pipeline("sentiment-analysis") # 文本分类模型
print(nlp("I like this book!"))
# [{'label': 'POSITIVE', 'score': 0.9998674392700195}]
# 输出结果的前两行是下载模型的信息，最后一行是模型输出的结果。

# 代码实现：完成特征提取任务
from transformers import *
import numpy as np
nlp_features = pipeline('feature-extraction')
output = nlp_features('Shanxi University is a university in Shanxi.')
print(np.array(output).shape)
# (1, 12, 768)

# 代码实现：完成完形填空任务
from transformers import *
nlp_fill = pipeline("fill-mask") # 文本分类模型
print(nlp_fill.tokenizer.mask_token)
print(nlp_fill(f"Li Jinhong wrote many {nlp_fill.tokenizer.mask_token} about artificial intelligence technology and helped many people."))
# 从输出结果中可以看出，模型输出了分值最大的前5名结果。其中第1行的结果预测出了被遮蔽的单词为books
#  [{'score': 0.5444340109825134, 'token': 2799, 'token_str': ' books', 'sequence': 'Li Jinhong wrote many books about artificial intelligence technology and helped many people.'}, 
#  {'score': 0.32027241587638855, 'token': 7201, 'token_str': ' articles', 'sequence': 'Li Jinhong wrote many articles about artificial intelligence technology and helped many people.'},
#  {'score': 0.024945968762040138, 'token': 27616, 'token_str': ' essays', 'sequence': 'Li Jinhong wrote many essays about artificial intelligence technology and helped many people.'}, 
#  {'score': 0.021165795624256134, 'token': 6665, 'token_str': ' papers', 'sequence': 'Li Jinhong wrote many papers about artificial intelligence technology and helped many people.'}, 
#  {'score': 0.018288355320692062, 'token': 22064, 'token_str': ' blogs', 'sequence': 'Li Jinhong wrote many blogs about artificial intelligence technology and helped many people.'}]

# 代码实现：完成阅读理解任务
from transformers import *
nlp_qa = pipeline("question-answering")
context = 'Shanxi University is a university in Shanxi.'
question = 'Where is Shanxi University?'
print(nlp_qa(context = context,question = question))
# {'score': 0.926823079586029, 'start': 37, 'end': 43, 'answer': 'Shanxi'}

# 代码实现：完成摘要生成任务【太大了，没运行】
from transformers import *
TEXT_TO_SUMMARIZE = '''
In this notebook we will be using the transformer model, first introduced in this paper. Specifically, we will be using the BERT (Bidirectional Encoder Representations from Transformers) model from this paper.
Transformer models are considerably larger than anything else covered in these tutorials. As such we are going to use the transformers library to get pre-trained transformers and use them as our embedding layers. We will freeze (not train) the transformer and only train the remainder of the model which learns from the representations produced by the transformer. In this case we will be using a multi-layer bi-directional GRU, however any model can learn from these representations.
'''
summarizer = pipeline('summarization')
print(summarizer(TEXT_TO_SUMMARIZE))

# 代码实现:完成实体词识别任务【太大了，没运行】
from transformers import *
nlp_token_class = pipeline("ner")
print(nlp_token_class('Shanxi University is a university in Shanxi.'))

# 代码实现：完成摘要生成任务
# 在摘要任务的基础上，加载自定义模型，并完成预测。
from transformers import *
TEXT_TO_SUMMARIZE = '''
In this notebook we will be using the transformer model, first introduced in this paper. Specifically, we will be using the BERT (Bidirectional Encoder Representations from Transformers) model from this paper.
Transformer models are considerably larger than anything else covered in these tutorials. As such we are going to use the transformers library to get pre-trained transformers and use them as our embedding layers. We will freeze (not train) the transformer and only train the remainder of the model which learns from the representations produced by the transformer. In this case we will be using a multi-layer bi-directional GRU, however any model can learn from these representations.
'''
# 官方模板
# summarizer = pipeline('summarization')
# 自定义模板
tokenizer = AutoTokenizer.from_pretrained(r'./bart-large-cnn/')
summarizer = pipeline("summarization", model=r'./bart-large-cnn/', tokenizer=tokenizer)
print(summarizer(TEXT_TO_SUMMARIZE))