context_models.py 文件源码

def __init__(self, deep, gpu, word2index, in_units, hidden_units, out_units, loss_func, train, drop_ratio=0.0):
        n_vocab = len(word2index)        
        l2r_embedding=F.EmbedID(n_vocab, in_units)
        r2l_embedding=F.EmbedID(n_vocab, in_units)

        if deep:
            super(BiLstmContext, self).__init__(
                l2r_embed=l2r_embedding,
                r2l_embed=r2l_embedding,
                loss_func=loss_func,
                l2r_1 = L.LSTM(in_units, hidden_units),
                r2l_1 = L.LSTM(in_units, hidden_units),
                l3 = L.Linear(2*hidden_units, 2*hidden_units),
                l4 = L.Linear(2*hidden_units, out_units),
            )
        else:
            super(BiLstmContext, self).__init__(
                l2r_embed=l2r_embedding,
                r2l_embed=r2l_embedding,
                loss_func=loss_func,
                l2r_1 = L.LSTM(in_units, hidden_units),
                r2l_1 = L.LSTM(in_units, hidden_units),
                lp_l2r = L.Linear(hidden_units, out_units/2),
                lp_r2l = L.Linear(hidden_units, out_units/2)

            )
        if gpu >=0:
            self.to_gpu()
        l2r_embedding.W.data = self.xp.random.normal(0, math.sqrt(1. / l2r_embedding.W.data.shape[0]), l2r_embedding.W.data.shape).astype(np.float32)       
        r2l_embedding.W.data = self.xp.random.normal(0, math.sqrt(1. / r2l_embedding.W.data.shape[0]), r2l_embedding.W.data.shape).astype(np.float32)

        self.word2index = word2index
        self.train = train
        self.deep = deep
        self.drop_ratio = drop_ratio