Transformers实际应用案例

首先安装transformers
>pip install transformers

from transformers import pipeline

---

API例子1–情感分类

首先需要下载并缓存预训练模型

classifier = pipeline('sentiment-analysis')

尝试输入一段文本，预训练模型会给出相应的情感类别，和相应的置信度分数

classifier('这部电影真的很垃圾，浪费我的时间！！！')

classifier('this movie is really great! I love it')

---

API例子二–智能填词(Masked Language Modeling)

下载并缓存预训练模型

unmask = pipeline('fill-mask')

尝试输入一段有空缺的句子，观察被填补的空缺是否符合真实情况

from pprint import pprint
results1 = unmask(f'{unmask.tokenizer.mask_token} is the most beatiful woman in Harry Potter!')
results2 = unmask(f'{unmask.tokenizer.mask_token} is the best player in the NBA!')
pprint(results1)
pprint(results2)

---

API例子三–文本生成

下载并缓存预训练模型

from transformers import pipeline, set_seed
generator = pipeline('text-generation', model='gpt2')
set_seed(42)

generator("Xiao ming loves Xiao Hong secretly,",max_length=100, num_return_sequences=5)

更多的任务pipeline API可以在下面的网站找到:

https://huggingface.co/transformers/task_summary.html