python - gensim word2vec - 在线词嵌入更新中的数组维度

Question

来自 gensim 0.13.4.1 的 Word2Vec 无法动态更新词向量。

model.build_vocab(sentences, update=False)

工作正常；然而，

model.build_vocab(sentences, update=True)

没有。

---

我正在使用 this website尝试效仿他们所做的事情；因此我在某些时候使用了以下脚本:

model = gensim.models.Word2Vec()
sentences = gensim.models.word2vec.LineSentence("./text8/text8")
model.build_vocab(sentences, keep_raw_vocab=False, trim_rule=None, progress_per=10000, update=False)
model.train(sentences)

然而，当它使用 update=False 运行时，使用 update=True 给我以下回溯:

Traceback (most recent call last):
  File "word2vecAttempt.py", line 34, in <module>
    model.build_vocab(sentences, progress_per=10000, update=True)
  File "/home/brownc/anaconda3/lib/python3.5/site-packages/gensim/models/word2vec.py", line 535, in build_vocab
    self.finalize_vocab(update=update)  # build tables & arrays
  File "/home/brownc/anaconda3/lib/python3.5/site-packages/gensim/models/word2vec.py", line 708, in finalize_vocab
    self.update_weights()
  File "/home/brownc/anaconda3/lib/python3.5/site-packages/gensim/models/word2vec.py", line 1070, in update_weights
    self.wv.syn0 = vstack([self.wv.syn0, newsyn0])
  File "/home/brownc/anaconda3/lib/python3.5/site-packages/numpy/core/shape_base.py", line 230, in vstack
    return _nx.concatenate([atleast_2d(_m) for _m in tup], 0)
ValueError: all the input array dimensions except for the concatenation axis must match exactly

Answer 1

我能够重现您的错误。我认为您在模型尚未训练时调用 update=True。您应该只在它经过预训练后调用它。

这个有效:

import gensim

model = gensim.models.Word2Vec()
sentences = gensim.models.word2vec.LineSentence("text8")
model.build_vocab(sentences, update=False)
model.train(sentences)

model.build_vocab(sentences, update=True)
model.train(sentences)

但这会失败:

import gensim

model = gensim.models.Word2Vec()
sentences = gensim.models.word2vec.LineSentence("text8")
model.build_vocab(sentences, update=True)
model.train(sentences)

ValueError: all the input array dimensions except for the concatenation axis must match exactly

使用最新版本的gensim 0.13.4.1。