Closed TobiasEl closed 6 years ago
You need to use my forked version of gensim: https://github.com/jhlau/gensim
I did use the forked version. conda list shows version 0.12.4. But when I do
model = Doc2Vec.load("/data/doc2vec/apnews_dbow/doc2vec.bin")
for both of the pretrained doc2vec models, I always get UnicodeDecodeError: 'ascii' codec can't decode byte 0xfb in position 1: ordinal not in range(128)
why is this happening?
@bhomass @TobiasEl did you manage to sort this issue out? I am also struggling to load the pretrained embeddings...
I have the same issue as @TobiasEl and I get the same error whether I load the master branch or the develop branch.
Hi. Im loading the pretrained model Doc2Vec from English Wikipedia (in the same folder I have the .bin and the syn0 and syn1. But when I load the model I have the error: 'Doc2Vec' object has no attribute 'batch_words'. It seems that the problem is due to diferents versions of gensim. Could you help me please?
Here is the complete error message: `` AttributeErrorTraceback (most recent call last)