load_langmod.py 文件源码

def load_pretrained():

    #glove_vec = ["glove_wiki_50","glove_wiki_150","glove_wiki_300"]
    glove_vec = ["glove_wiki_300"]
    #glove_vec = ["glove_wiki_50"]
    filename = 'glove_pretrained.h5'
    #import tensorflow as tf
    #sess = tf.InteractiveSession()

    features, words = load_h5py('glove_wiki_300',filename=root + glove_vec_fold + filename)
    filename = 'glove.h5'
    features = normalize(np.array(features), axis=1, norm='l2')
    with h5py.File(root + glove_vec_fold + filename, "w") as hf:
        hf.create_dataset(glove_vec[0], data=features)
        string_dt = h5py.special_dtype(vlen=str)
        hf.create_dataset(glove_vec[0] + "_words", data=words, dtype=string_dt)

    for vec in glove_vec:
        data, words = load_h5py(vec, filename=root + glove_vec_fold + "glove.h5")
        print(data.shape, words.shape)
        time.sleep(5)