训练 spaCy - NameError

Question

我需要训练 spaCy 模型来提高识别产品的准确性。我正在努力训练我的 spacy 模型。我有以下代码：

TRAIN_DATA = [('..., {'entities': [(36,55,'PRODUCT')]})]
nlp = spacy.load("en_core_web_lg")
ner = nlp.get_pipe("ner")

optimizer = nlp.create_optimizer()
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != "ner"]

with nlp.disable_pipes(*other_pipes): # only train NER
    for itn in range(50):
        random.shuffle(TRAIN_DATA)
        losses = {}
        for text, annotations in TRAIN_DATA:
            doc = nlp.make_doc(text)
            example = Example.from_dict(doc, annotations)
            nlp.update([example], drop=0.25, sgd=optimizer, losses=losses)

但由于以下原因而失败：

NameError                                 Traceback (most recent call last)
<ipython-input-4-903f2be7114f> in <module>
     15         for text, annotations in TRAIN_DATA:
     16             doc = nlp.make_doc(text)
---> 17             example = Example.from_dict(doc, annotations)
     18             nlp.update([example], drop=0.25, sgd=optimizer, losses=losses)
     19 print(losses)

NameError: name 'Example' is not defined

我需要如何定义Example？

Answer 1

这里很热... 感谢提示我错过了导入：来自 spacy.training 导入示例

将代码从 Jupyter 移动到 Visual Studio 部署代码时

训练 spaCy - NameError

Training spaCy - NameError

python

nlp

spacy