实例4：循环神经网络RNN之情感分类问题（SimpleRNNCell实现）

前言

SimpleRNNCell是更加底层的方法进行构造RNN神经网络来进行情感分析，能够帮助你更好的理解RNN网络

循环网络示意图：

采用了权值共享的思想

完整代码及相应注释如下：

import os
import tensorflow as tf
import numpy as np
from tensorflow import keras
from tensorflow.keras import layers
 
tf.random.set_seed(22)
np.random.seed(22)
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
assert tf.__version__.startswith('2.')
 
batchsz = 128
total_words = 10000  #常用的10000个，当出现生僻字时把它当成一个单词
max_review_len = 80
embedding_len = 100
(x_train,y_train),(x_test,y_test)=keras.datasets.imdb.load_data(num_word=total_words) # 只给常见的10000个单词进行编码
# 每个句子长度不等，将多个句子padding成相同长度的句子
# x_train:[b,80]
# x_test:[b,80]
x_train = keras.preprocessing.sequence.pad_sequences(x_train,maxlen=max_review_len)
x_test = keras.preprocessing.sequence.pad_sequences(x_test,maxlen=max_review_len)
 
db_train = tf.data.Dataset.from_tensor_slices((x_train,y_train))
db_train = db_train.shuffle(1000).batch(batchsz,drop_remainder=True)   # 当最后一个batchsize小于128时，丢弃
db_test = tf.data.Dataset.from_tensor_slices((x_test,y_test))
db_test = db_test.batch(batchsz,drop_remainder=True)
print('x_train shape:',x_train.shape,tf.reduce_max(y_train),tf.reduce_min(y_train))
print('x_test:',x_test.shape)
 
 
class MyRNN(keras.Model):
 
    def __init__(self,units):
        super(MyRNN,self).__init__()
 
        # [b,64]
        self.state0 = [tf.zeros([batchsz,units])]
        self.state1 = [tf.zeros([batchsz, units])]
        #  [b,80]  >>  [b,80,100]
        self.embedding = layers.Embedding(total_words,embedding_len,input_len = max_review_len)
 
 
        # [b,80,100],  h_dim:64
        # SimpleRNN
        self.rnn_cell0 = layers.SimpleRNNCell(units,dropout=0.2)  #防止过拟合
        self.rnn_cell1 = layers.SimpleRNNCell(units,dropout=0.2)
 
 
        # fc   [b,80,100]>>[b,64]>>[b,1]
        self.outlayer = layers.Dense(1)
 
 
    def call(self,inputs,training=None):
        '''
        net(x) net(x,training=True)  :train mode
        nex(x,training = False) : test mode
        :param inputs: [b,80]
        :param training:
        :return:
        '''
        # [b,80]
        x = inputs
        # embedding : [b,80]>>[b,80,100]
        x = self.embedding(x)
        # rnn cell comute
        # [b,80,100]>>[b,64]
        state0 = self.state0
        state1 = self.state1
        for word in tf.unstack(x,axis=1): # word:[b,100]  希望在第二个维度或者单词维度展开
           # h1 = x*wxh+h*whh
           out0,state0 = self.rnn_cell0(word,state0,training) # 注意传入training参数，令其可以在不同模式下操作.及是否使用dropout
           out1,state1 = self.rnn_cell1(out0,state1)
 
 
        # out:[b,64]>>[b,1]
        x = self.outlayer(out1)
        # p(y is pos|x)
        prob = tf.sigmoid(x)
 
        return prob
 
 
 
 
def main():
    units = 64
    epochs = 4
 
    model = MyRNN(units)
    model.compile(optimizer = keras.optimizers.Adam(0.001),
                  loss = tf.losses.BinaryCrossentropy(),
                  metrics = ['accuracy'])
    model.fit(db_train,epochs = epochs,validation = db_test)
 
    model.evaluate(db_test)
 
 
 
 
 
 
if __name__ == '__main__':
        main()

本文代码和图片来自：

课时114 RNN与情感分类问题实战-加载IMDB数据集_哔哩哔哩_bilibili