E
Size: a a a
E
K
ip
K
AP
M
for epoch in range(100):
for batch in spacy.util.minibatch(train_data, size=2):
for text, annotations in batch:
doc = nlp.make_doc(text)
example = Example.from_dict(doc, annotations)
nlp.update([example], sgd=optimizer, drop=0.2, losses=losses)
print('loss: '+str(losses['textcat']))
ЕТ
DD
D•
AW
D•
MF
NK
М
DD