手把手教你使用TensorFlow2实现RNN

class RNN(tf.keras.Model):

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

        # 初始化 [b, 64] (b 表示 batch_size)
        self.state0 = [tf.zeros([batch_size, units])]
        self.state1 = [tf.zeros([batch_size, units])]

        # [b, 80] => [b, 80, 100]
        self.embedding = tf.keras.layers.Embedding(total_words, embedding_len, input_length=max_review_len)

        self.rnn_cell0 = tf.keras.layers.SimpleRNNCell(units=units, dropout=0.2)
        self.rnn_cell1 = tf.keras.layers.SimpleRNNCell(units=units, dropout=0.2)

        # [b, 80, 100] => [b, 64] => [b, 1]
        self.out_layer = tf.keras.layers.Dense(1)

    def call(self, inputs, training=None):
        """

        :param inputs: [b, 80]
        :param training:
        :return:
        """

        state0 = self.state0
        state1 = self.state1

        x = self.embedding(inputs)

        for word in tf.unstack(x, axis=1):
            out0, state0 = self.rnn_cell0(word, state0, training=training)
            out1, state1 = self.rnn_cell1(out0, state1, training=training)

        # [b, 64] -> [b, 1]
        x = self.out_layer(out1)

        prob = tf.sigmoid(x)

        return prob

def get_data():
    # 获取数据
    (X_train, y_train), (X_test, y_test) = tf.keras.datasets.imdb.load_data(num_words=total_words)

    # 更改句子长度
    X_train = tf.keras.preprocessing.sequence.pad_sequences(X_train, maxlen=max_review_len)
    X_test = tf.keras.preprocessing.sequence.pad_sequences(X_test, maxlen=max_review_len)

    # 调试输出
    print(X_train.shape, y_train.shape)  # (25000, 80) (25000,)
    print(X_test.shape, y_test.shape)  # (25000, 80) (25000,)

    # 分割训练集
    train_db = tf.data.Dataset.from_tensor_slices((X_train, y_train))
    train_db = train_db.shuffle(10000).batch(batch_size, drop_remainder=True)

    # 分割测试集
    test_db = tf.data.Dataset.from_tensor_slices((X_test, y_test))
    test_db = test_db.batch(batch_size, drop_remainder=True)

    return train_db, test_db

import tensorflow as tf


class RNN(tf.keras.Model):

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

        # 初始化 [b, 64]
        self.state0 = [tf.zeros([batch_size, units])]
        self.state1 = [tf.zeros([batch_size, units])]

        # [b, 80] => [b, 80, 100]
        self.embedding = tf.keras.layers.Embedding(total_words, embedding_len, input_length=max_review_len)

        self.rnn_cell0 = tf.keras.layers.SimpleRNNCell(units=units, dropout=0.2)
        self.rnn_cell1 = tf.keras.layers.SimpleRNNCell(units=units, dropout=0.2)

        # [b, 80, 100] => [b, 64] => [b, 1]
        self.out_layer = tf.keras.layers.Dense(1)

    def call(self, inputs, training=None):
        """

        :param inputs: [b, 80]
        :param training:
        :return:
        """

        state0 = self.state0
        state1 = self.state1

        x = self.embedding(inputs)

        for word in tf.unstack(x, axis=1):
            out0, state0 = self.rnn_cell0(word, state0, training=training)
            out1, state1 = self.rnn_cell1(out0, state1, training=training)

        # [b, 64] -> [b, 1]
        x = self.out_layer(out1)

        prob = tf.sigmoid(x)

        return prob


# 超参数
total_words = 10000  # 文字数量
max_review_len = 80  # 句子长度
embedding_len = 100  # 词维度
batch_size = 1024  # 一次训练的样本数目
learning_rate = 0.0001  # 学习率
iteration_num = 20  # 迭代次数
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)  # 优化器
loss = tf.losses.BinaryCrossentropy(from_logits=True)  # 损失
model = RNN(64)

# 调试输出summary
model.build(input_shape=[None, 64])
print(model.summary())

# 组合
model.compile(optimizer=optimizer, loss=loss, metrics=["accuracy"])


def get_data():
    # 获取数据
    (X_train, y_train), (X_test, y_test) = tf.keras.datasets.imdb.load_data(num_words=total_words)

    # 更改句子长度
    X_train = tf.keras.preprocessing.sequence.pad_sequences(X_train, maxlen=max_review_len)
    X_test = tf.keras.preprocessing.sequence.pad_sequences(X_test, maxlen=max_review_len)

    # 调试输出
    print(X_train.shape, y_train.shape)  # (25000, 80) (25000,)
    print(X_test.shape, y_test.shape)  # (25000, 80) (25000,)

    # 分割训练集
    train_db = tf.data.Dataset.from_tensor_slices((X_train, y_train))
    train_db = train_db.shuffle(10000).batch(batch_size, drop_remainder=True)

    # 分割测试集
    test_db = tf.data.Dataset.from_tensor_slices((X_test, y_test))
    test_db = test_db.batch(batch_size, drop_remainder=True)

    return train_db, test_db


if __name__ == "__main__":
    # 获取分割的数据集
    train_db, test_db = get_data()

    # 拟合
    model.fit(train_db, epochs=iteration_num, validation_data=test_db, validation_freq=1)