基本信息

---

下载

   友情提示：（无需注册或充值，赞助后即可获取资源下载链接）

---

     嘿，亲！知识可是无价之宝呢，但咱这精心整理的资料也耗费了不少心血呀。小小地破费一下，绝对物超所值哦！如有下载和支付问题，请联系我们QQ(微信同号)：813200300

本次赞助数额为： 2 元　

支付宝支付

微信支付

   源码介绍

---

class MyRNN(keras.Model):

    def __init__(self, units):
        super(MyRNN, self).__init__()


        # transform text to embedding representation
        # [b, 80] => [b, 80, 100]
        self.embedding = layers.Embedding(total_words, embedding_len,
                                          input_length=max_review_len)

        # [b, 80, 100] , h_dim: 64
        self.rnn = keras.Sequential([
            # layers.SimpleRNN(units, dropout=0.5, return_sequences=True, unroll=True),
            # layers.SimpleRNN(units, dropout=0.5, unroll=True)

            layers.LSTM(units, dropout=0.5, return_sequences=True, unroll=True),
            layers.LSTM(units, dropout=0.5, unroll=True)
        ])


        # fc, [b, 80, 100] => [b, 64] => [b, 1]
        self.outlayer = layers.Dense(1)