每次迭代后保存 spacy 的 NER 模型

Question

我试图在每次迭代后保存到 Spacy 自定义 NER 模型。我们是否有任何类似于 tensorflow 中的 API 来在每个/某些没有之后保存模型权重。的迭代。然后我可以重新加载保存的模型并从那里继续训练。

另外，我如何在 linux 中使用我系统上的所有内核。我发现四个核心中只有两个被使用。他们将多任务 CNN 用于 NER，我知道这需要更多时间在 CPU 上重新训练。还有其他加快 NER 模型训练的方法。

@plac.annotations(
    model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
    output_dir=("Optional output directory", "option", "o", Path),
    n_iter=("Number of training iterations", "option", "n", int))
def main(model=None, output_dir=None, n_iter=100):
    """Load the model, set up the pipeline and train the entity recognizer."""
    if model is not None:
        nlp = spacy.load(model)  # load existing spaCy model
        print("Loaded model '%s'" % model)
    else:
        nlp = spacy.blank('en')  # create blank Language class
        print("Created blank 'en' model")

    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])

    other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'ner']
    with nlp.disable_pipes(*other_pipes):  # only train NER
        optimizer = nlp.begin_training()
        for itn in range(n_iter):
            random.shuffle(TRAIN_DATA)
            losses = {}
            for text, annotations in TRAIN_DATA:
                nlp.update(
                    [text],  # batch of texts
                    [annotations],  # batch of annotations
                    drop=0.5,  # dropout - make it harder to memorise data
                    sgd=optimizer,  # callable to update weights
                    losses=losses)
            print(losses)

    # 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)

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

Answer 1

要在每次迭代后保存您的模型，您只需将最后一段代码移动到循环中即可。例如：

@plac.annotations(
    model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
    output_dir=("Optional output directory", "option", "o", Path),
    n_iter=("Number of training iterations", "option", "n", int))

def main(model=None, output_dir=None, n_iter=100):
    """Load the model, set up the pipeline and train the entity recognizer."""
    if model is not None:
        nlp = spacy.load(model)  # load existing spaCy model
        print("Loaded model '%s'" % model)
    else:
        nlp = spacy.blank('en')  # create blank Language class
        print("Created blank 'en' model")

    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])

    other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'ner']
    with nlp.disable_pipes(*other_pipes):  # only train NER
        optimizer = nlp.begin_training()
        for itn in range(n_iter):
            random.shuffle(TRAIN_DATA)
            losses = {}
            for text, annotations in TRAIN_DATA:
                nlp.update(
                    [text],  # batch of texts
                    [annotations],  # batch of annotations
                    drop=0.5,  # dropout - make it harder to memorise data
                    sgd=optimizer,  # callable to update weights
                    losses=losses)
            print(losses)
                # save model to output directory
            if output_dir is not None:
                output_dir = Path(output_dir+str(int))
                if not output_dir.exists():
                    output_dir.mkdir()
                nlp.to_disk(output_dir)
                print("Saved model to", output_dir)



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

只需在每个循环中修改字符串，以免每次都覆盖最新的保存。