Model() 得到参数 'nr_class' 的多个值 - SpaCy 多分类模型（BERT 集成）

Question

您好，我正在使用新的 SpaCy 模型 en_pytt_bertbaseuncased_lg 实现多分类模型 (5 类)。新管道的代码在这里：

nlp = spacy.load('en_pytt_bertbaseuncased_lg')
textcat = nlp.create_pipe(
    'pytt_textcat',
    config={
        "nr_class":5,
        "exclusive_classes": True,
    }
)
nlp.add_pipe(textcat, last = True)

textcat.add_label("class1")
textcat.add_label("class2")
textcat.add_label("class3")
textcat.add_label("class4")
textcat.add_label("class5")

训练代码如下，基于此处的示例(https://pypi.org/project/spacy-pytorch-transformers/):

def extract_cat(x):
    for key in x.keys():
        if x[key]:
            return key

# get names of other pipes to disable them during training
n_iter = 250 # number of epochs

train_data = list(zip(train_texts, [{"cats": cats} for cats in train_cats]))


dev_cats_single   = [extract_cat(x) for x in dev_cats]
train_cats_single = [extract_cat(x) for x in train_cats]
cats = list(set(train_cats_single))
recall = {}
for c in cats:
    if c is not None: 
        recall['dev_'+c] = []
        recall['train_'+c] = []



optimizer = nlp.resume_training()
batch_sizes = compounding(1.0, round(len(train_texts)/2), 1.001)

for i in range(n_iter):
    random.shuffle(train_data)
    losses = {}
    batches = minibatch(train_data, size=batch_sizes)
    for batch in batches:
        texts, annotations = zip(*batch)
        nlp.update(texts, annotations, sgd=optimizer, drop=0.2, losses=losses)
    print(i, losses)

所以我的数据结构如下所示：

[('TEXT TEXT TEXT',
  {'cats': {'class1': False,
    'class2': False,
    'class3': False,
    'class4': True,
    'class5': False}}), ... ]

我不确定为什么会出现以下错误：

TypeError                                 Traceback (most recent call last)
<ipython-input-32-1588a4eadc8d> in <module>
     21 
     22 
---> 23 optimizer = nlp.resume_training()
     24 batch_sizes = compounding(1.0, round(len(train_texts)/2), 1.001)
     25 

TypeError: Model() got multiple values for argument 'nr_class'

编辑：

如果我去掉 nr_class 参数，我会在这里得到这个错误：

ValueError: operands could not be broadcast together with shapes (1,2) (1,5)

我实际上认为这会发生，因为我没有指定 nr_class 参数。那是对的吗？

Answer 1

这是我们发布的 spacy-pytorch-transformers 最新版本的回归。对此感到抱歉！

究其根本，这又是**kwargs的弊端。我期待改进 spaCy API 以防止将来出现这些问题。

您可以在此处查看违规行：https://github.com/explosion/spacy-pytorch-transformers/blob/c1def95e1df783c69bff9bc8b40b5461800e9231/spacy_pytorch_transformers/pipeline/textcat.py#L71。我们提供 nr_class 位置参数，它与您在配置期间传入的显式参数重叠。

为了解决该问题，您只需从要传递给 spacy.create_pipe().

的 config 字典中删除 nr_class 键

Model() 得到参数 'nr_class' 的多个值 - SpaCy 多分类模型（BERT 集成）

Model() got multiple values for argument 'nr_class' - SpaCy multi-classification model (BERT integration)

python

spacy

multiclass-classification

pytorch

spacy-transformers