七、Tensorflow实现RNN

目录

7-1 使用简单的RNN的变体LSTM实现手写体的分类

---

关于RNN的理论知识可以参考另外两篇博客，

    https://blog.csdn.net/qq_22169787/article/details/82154485

    https://blog.csdn.net/qq_22169787/article/details/82150841

7-1 使用简单的RNN的变体LSTM实现手写体的分类

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#载入数据集
mnist = input_data.read_data_sets('MNIST_data',one_hot=True)

#载入图片是28*28
n_inputs = 28#输入一行一共有28个数据
max_time = 28#一共28行
lstm_size = 100#隐藏层单元
n_class = 10#10个分类
batch_size = 50#每批次50个样本
n_batch = mnist.train.num_examples // batch_size#一共计算有多少个批次

x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])

#初始化权重
weights = tf.Variable(tf.truncated_normal([lstm_size, n_class], stddev=0.1))
#初始化偏置值
biases = tf.Variable(tf.constant(0.1,shape=[n_class]))

#定义RNN网络
def RNN(X,weights,biases):
    # inputs=[batch_size, max_time, n_inputs]
    inputs = tf.reshape(X,[-1,max_time,n_inputs])
    #定义LSTM基本CELL
    lstm_cell = tf.contrib.rnn.BasicLSTMCell(lstm_size)#将它更改tf.contrib.rnn.core_rnn_cell.BasicLSTMCell(lstm_size)，已经失效
    # final_state[0]是cell state
    # final_state[1]是hidden_state
    outputs,final_state = tf.nn.dynamic_rnn(lstm_cell,inputs,dtype=tf.float32)
    results = tf.nn.softmax(tf.matmul(final_state[1],weights) + biases)
    return results

#计算RNN的返回结果
prediction= RNN(x, weights, biases)  
#损失函数
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y))
#使用AdamOptimizer进行优化
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
#结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax返回一维张量中最大的值所在的位置
#求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))#把correct_prediction变为float32类型
#初始化
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(6):
        for batch in range(n_batch):
            batch_xs,batch_ys =  mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys})
        
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
        print ("Iter " + str(epoch) + ", Testing Accuracy= " + str(acc))

Extracting MNIST_data\train-images-idx3-ubyte.gz
Extracting MNIST_data\train-labels-idx1-ubyte.gz
Extracting MNIST_data\t10k-images-idx3-ubyte.gz
Extracting MNIST_data\t10k-labels-idx1-ubyte.gz
Iter 0, Testing Accuracy= 0.7652
Iter 1, Testing Accuracy= 0.8879
Iter 2, Testing Accuracy= 0.9142
Iter 3, Testing Accuracy= 0.9234
Iter 4, Testing Accuracy= 0.937
Iter 5, Testing Accuracy= 0.9334

 

说明：1.关于tensorflow的代码是参考了b站练数成金的代码，链接地址：https://www.bilibili.com/video/av20542427/?p=1

           2.部分代码还参考了tensorflow中文社区的网站，以及tensorflow的官网（需要梯子）。

           tensorflow中文社区的网站：http://www.tensorfly.cn/

   MNIST_data手写数据集下载：链接：https://pan.baidu.com/s/1_PxLxxZ4YP7KfDzZh8vPFA 密码：nyrs

   更多Tensorflow资源下载，去github搜索Tensorflow下载更多demo