读取cn.skipgram.bin.tar.gz错误

[Jacky-Chiu]

model = gensim.models.KeyedVectors.load_word2vec_format(fdir + 'cn.skipgram.bin.tar.gz', binary=True)

ValueError: invalid literal for int() with base 10: 'cn.skipgram.bin\x00\x00。。。。。。

你好，读取cn.skipgram.bin.tar.gz文件出现这个错误，查了很久都不知道原因

[Senmumu]

解压后再试试？

[Senmumu]

can you unzip this file and try again?

[to-shimo]

请参考Mikolov的word2vec的源码读取方式

[hy9be]

I got 'utf-8' codec can't decode bytes in position 96-97: unexpected end of data when I try to load the unzipped bin file.

[liyonglion]

我使用gensim 加载，未解压的模型，报错：utf-8' codec can't decode bytes in position 96-97: unexpected end of data。如何加载这个模型呢？

[yydai]

Using like this can work for me:

word2vec = gensim.models.KeyedVectors.load_word2vec_format( 'XXX', binary=True, unicode_errors='ignore')