load_glove

load_glove.py

### load word2vec model ###
#pre-train model download from: https://github.com/stanfordnlp/GloVe
#preprocess:https://stackoverflow.com/questions/51323344/cant-load-glove-6b-300d-txt
wvmodel = gensim.models.KeyedVectors.load_word2vec_format('glove.6B.100d.w2vformat.txt',binary=False, encoding='utf-8')

## map golve pretrain weight to pytorch embedding pretrain weight
embed_size = 100
weight = torch.zeros(vocab_size+1, embed_size) #given 0 if the word is not in glove
for i in range(len(wvmodel.index2word)):
    try:
        index = word_to_idx[wvmodel.index2word[i]] #transfer to our word2ind
    except:
        continue
    weight[index, :] = torch.from_numpy(wvmodel.get_vector(wvmodel.index2word[i]))