文本的embedding

使用：word2vec进行文本的embedding

VECTOR_DIR = 'GoogleNews-vectors-negative300.bin' # 词向量模型文件

from keras.utils import plot_model
from keras.layers import Embedding
import gensim
from gensim.models import Word2Vec
EMBEDDING_DIM = 300 # 词向量空间维度
w2v_model = gensim.models.KeyedVectors.load_word2vec_format(VECTOR_DIR, binary=True)
embedding_matrix = np.zeros((len(word_index) + 1, EMBEDDING_DIM))
for word, i in word_index.items(): 
    if unicode(word) in w2v_model:
        embedding_matrix[i] = np.asarray(w2v_model[unicode(word)],
                                         dtype='float32')
embedding_layer = Embedding(len(word_index) + 1,
                            EMBEDDING_DIM,
                            weights=[embedding_matrix],
                            input_length=500,