SpaCy - ValueError：操作数无法与形状一起广播（1,2）（1,5）

Question

关于 stackoverflow 上的上一篇文章 Model() got multiple values for argument 'nr_class' - SpaCy multi-classification model (BERT integration) 我的问题已部分解决 我想分享实施解决方案后出现的问题。

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 争论。这是正确的吗？

再写一次我的多类模型代码：

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")

训练的代码如下，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)

所以我的数据结构是这样的：

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

Answer 1

正如@Milla Well 已经评论的那样，可以在here 找到答案（来自@syllogism_ 的github 上的错误修复）