Posts

Showing posts with the label word-embedding

Words from word2vec not present in TensorBoard

Image
Words from word2vec not present in TensorBoard I'm working on a project which is needed to use word2vec. when I run my simple code everything gonna be ok but while I use tensorboard to see my result, I just face a 3D vector with JUST THE FIRST LITTER OF SOME WORDS! **my corpus is in english and have 1000 sentences **at first I didn't token my corpus but now I do Why should I do??? and here is my code: import logging import gensim from gensim.models.word2vec import Word2Vec vector_size = 512 window_size = 10 logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO) word2vec = Word2Vec (sentences='dataset.csv',size=200 ,window=10,negative=20,seed=1000,min_count=1) word2vec.save('text646.model') word2vec.wv.save_word2vec_format('text.model.bin', binary=True) model= gensim.models.KeyedVectors.load_word2vec_format('text.model.bin', binary=True) Here is a screen shot from tensorbord: thank alot ...