Word2Vec python ValueError:需要超过0个值才能unp

Question

我在使用googlenews的w2v嵌入时遇到问题。 我下载了GoogleNews-vectors-negative300.bin.gz并在运行之后

gensim.models.KeyedVectors.load_word2vec_format('/home/slava/GoogleNews-vectors-negative300.bin.gz', binary=True)

我搞错了

IOerror: not a gzipped file

好的，我在控制台中运行gzip GoogleNews-vectors-negative300.bin，然后 file GoogleNews-vectors-negative300.bin.gz现在说，它实际上是gzip压缩的数据。 但是跑步

gensim.models.KeyedVectors.load_word2vec_format('/home/slava/GoogleNews-vectors-negative300.bin.gz', binary=True)

现在回来了

ValueError: need more than 0 values to unpack

完全回溯：

> ValueError                                Traceback (most recent call
> last) <ipython-input-9-c4eebc3bcdb0> in <module>()
>       1 
>       2 from gensim.models import Word2Vec
> ----> 3 model = gensim.models.KeyedVectors.load_word2vec_format('/home/slava/GoogleNews-vectors-negative300.bin.gz',
> binary=True)
> 
> /home/slava/anaconda2/lib/python2.7/site-packages/gensim/models/keyedvectors.pyc
> in load_word2vec_format(cls, fname, fvocab, binary, encoding,
> unicode_errors, limit, datatype)
>     205         with utils.smart_open(fname) as fin:
>     206             header = utils.to_unicode(fin.readline(), encoding=encoding)
> --> 207             vocab_size, vector_size = map(int, header.split())  # throws for invalid file format
>     208             if limit:
>     209                 vocab_size = min(vocab_size, limit)
> 
> ValueError: need more than 0 values to unpack

怎么解决这个问题？在

Answer 1

文件已损坏，重新下载已解决