Question

我正在尝试训练Spacy的en_core_web_lg模型。我从官方文档中获得了用于训练新模型的代码。但是我想在en_core_web_lg模型的顶部进行培训。

代码如下：

from __future__ import unicode_literals, print_function

import sys
import plac
import random
from pathlib import Path
import spacy
from spacy.util import minibatch, compounding

# training data Start
TRAIN_DATA = [("The model of machine is PC-234w and its serial number is 322424-AGX.", {"entities": [(24, 31, "PRODUCT")]}),("The model of machine is PC-234w and its serial number is 322424-AGX.", {"entities": [(57, 67, "PRODUCT")]})]
#Train data End
def main(model="en_core_web_lg", output_dir=None, n_iter=100):
    """Load the model, set up the pipeline and train the entity recognizer."""
    nlp = spacy.load(model)  # load existing spaCy model
    print("Loaded model '%s'" % model)


    # create the built-in pipeline components and add them to the pipeline
    # nlp.create_pipe works for built-ins that are registered with spaCy
    if "ner" not in nlp.pipe_names:
        ner = nlp.create_pipe("ner")
        nlp.add_pipe(ner, last=True)
    # otherwise, get it so we can add labels
    else:
        ner = nlp.get_pipe("ner")

    # add labels
    for _, annotations in TRAIN_DATA:
        for ent in annotations.get("entities"):
            ner.add_label(ent[2])

    # get names of other pipes to disable them during training
    other_pipes = [pipe for pipe in nlp.pipe_names if pipe != "ner"]
    with nlp.disable_pipes(*other_pipes):  # only train NER
        # reset and initialize the weights randomly – but only if we're
        # training a new model
        nlp.begin_training()
        for itn in range(n_iter):
            random.shuffle(TRAIN_DATA)
            losses = {}
            # batch up the examples using spaCy's minibatch
            batches = minibatch(TRAIN_DATA, size=compounding(4.0, 32.0, 1.001))
            for batch in batches:
                texts, annotations = zip(*batch)
                nlp.update(
                    texts,  # batch of texts
                    annotations,  # batch of annotations
                    drop=0.5,  # dropout - make it harder to memorise data
                    losses=losses,
                )
            print("Losses", losses)

    # test the trained model
    for text, _ in TRAIN_DATA:
        doc = nlp(text)
        print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
        print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])

    # save model to output directory
    if output_dir is not None:
        output_dir = Path(output_dir)
        if not output_dir.exists():
            output_dir.mkdir()
        nlp.to_disk(output_dir)
        print("Saved model to", output_dir)

        # test the saved model
        print("Loading from", output_dir)
        nlp2 = spacy.load("en_core_web_lg")
        for text, _ in TRAIN_DATA:
            doc = nlp2(text)
            print("Entities", [(ent.text, ent.label_) for ent in doc.ents])



if __name__ == "__main__":
    plac.call(main)

这是输出

Entities [('PC-234w', 'PRODUCT'), ('322424-AGX', 'PRODUCT')]
Tokens [('The', '', 2), ('model', '', 2), ('of', '', 2), ('machine', '', 2), ('is', '', 2), ('PC-234w', 'PRODUCT', 3), ('and', '', 2), ('its', '', 2), ('serial', '', 2), ('number', '', 2), ('is', '', 2), ('322424-AGX', 'PRODUCT', 3), ('.', '', 2)]

但是当我在不同的脚本中运行相同的模型时，它会给我带来不同的NER结果。

代码：

import spacy

nlp = spacy.load("en_core_web_lg")
doc = nlp(u"The model of machine is PC-234w and its serial number is 322424-AGX.")

for ent in doc.ents:
      print(ent.text, ent.label_)

输出：

PC-234w ORG

肯定我做错了什么，但我无法弄清楚是什么。

Train Spacy默认英语模型

0 个答案: