train.py 文件源码

def make_character_embedding_layer(word_index):
    embeddings = get_embeddings()
    nb_words = min(MAX_NB_WORDS, len(word_index))
    embedding_matrix = np.zeros((nb_words, EMBEDDING_DIM))

    for word, i in word_index.items():
        if i >= MAX_NB_WORDS:
            continue
        embedding_vector = embeddings.get(word)
        if embedding_vector is not None:
            embedding_matrix[i] = embedding_vector

    embedding_layer = Embedding(nb_words, EMBEDDING_DIM, weights=[embedding_matrix], input_length=MAX_SEQUENCE_LENGTH, trainable=False)
    return embedding_layer