python - Does maximum vocabulary count is related to word vector dimensions in Glove model -
i have implemented glove model following implementation link https://github.com/stanfordnlp/glove/tree/master/src. have specified max vocab parameter 100000000 while generating vocab.txt file , word vector dimensions 100 while training model , generated vectors.txt 100 dimensions. when trying evaluate word_analogy.py eval folder in above link, getting following error
file "c:\users\jayashree\anaconda2\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 714, in runfile execfile(filename, namespace) file "c:\users\jayashree\anaconda2\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 74, in execfile exec(compile(scripttext, filename, 'exec'), glob, loc) file "c:/users/jayashree/documents/1 billion words/word_analogy.py", line 77, in <module> w, vocab, ivocab = generate() file "c:/users/jayashree/documents/1 billion words/word_analogy.py", line 32, in generate w[vocab[word], :] = v valueerror: cannot copy sequence size 66 array axis dimension 100
i want know whether parameters specified during vocabulary file creation has effect on dimensions of vectors file
Comments
Post a Comment