SpaCy - 值错误:操作数无法与形状 (1,2) (1,5) 一起广播

Question

关于堆栈溢出的上一篇文章 Model(( 为参数"nr_class"获得了多个值 - SpaCy 多分类模型(BERT 集成(，其中我的问题部分已解决，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 论点。这是对的吗？

再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，基于这里的例子(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}}), ... ]

Answer 1

正如@Milla已经评论的那样，答案可以在这里找到(来自 @syllogism_ 的 github 上的错误修复(