2021寒假（28）

TensorFlow循环神经网络

实验原理

RNN的网络结构及原理

RNNs包含输入单元(Input units)，输入集标记为{x0,x1,...,xt,xt+1,...}，而输出单元(Output units)的输出集则被标记为{y0,y1,...,yt,yt+1.,..}。RNNs还包含隐藏单元(Hidden units)，我们将其输出集标记为{h0,h1,...,ht,ht+1,...}，这些隐藏单元完成了最为主要的工作。

它的网络结构如下：

 

各个变量的含义：

 

展开以后形式：

 

其中每个圆圈可以看作是一个单元，而且每个单元做的事情也是一样的，因此可以折叠成左半图的样子。用一句话解释RNN，就是一个单元结构重复使用。

RNN是一个序列到序列的模型，假设xt-1,xt,xt+1是一个输入：“我是中国“，那么ot-1,ot就应该对应”是”，”中国”这两个，预测下一个词最有可能是什么？就是ot+1应该是”人”的概率比较大。

完整代码

import numpy as np  
import tensorflow as tf  
from tensorflow.contrib import rnn  
from tensorflow.examples.tutorials.mnist import input_data  
import os  
os.environ["CUDA_VISIBLE_DEVICES"]="0"  
  
mnist = input_data.read_data_sets("E:/PycharmProjects/TensorFlow/基础/1.3/data", one_hot = True)
 
#Training Parameters  
learning_rate=0.001  
training_steps=10000  
batch_size=128  
display_step=200  
 
#Network Parameters  
num_input=28  
timesteps=28  
num_hidden=128  
num_classes=10  
 
#tf Graph input  
X=tf.placeholder("float",[None,timesteps,num_input])  
Y=tf.placeholder("float",[None,num_classes])  
 
# Define weights  
weights={  
    'out':tf.Variable(tf.random_normal([num_hidden,num_classes]))  
}  
biases={  
    'out':tf.Variable(tf.random_normal([num_classes]))  
}  
  
def RNN(x,weights,biases):  
    x=tf.unstack(x,timesteps,1)  
    #define a lstm cell with tensorflow  
    lstm_cell=rnn.BasicLSTMCell(num_hidden,forget_bias=1.0)  
 
    #Get lstm cell ouput  
    outputs,states=rnn.static_rnn(lstm_cell,x,dtype=tf.float32)  
 
    #Linear activation ,using rnn inner loop last output  
    return tf.matmul(outputs[-1],weights['out'])+biases['out']  
  
logits=RNN(X,weights,biases)  
prediction=tf.nn.softmax(logits)  
 
#Define loss and  optimizer  
loss_op=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(  
    logits=logits,labels=Y  
))  
optimizer=tf.train.GradientDescentOptimizer(learning_rate=learning_rate)  
train_op=optimizer.minimize(loss_op)  
 
#Evaluate model(with test logits,for dropout to be disabled)  
corrent_pred=tf.equal(tf.argmax(prediction,1),tf.argmax(Y,1))  
accuracy=tf.reduce_mean(tf.cast(corrent_pred,tf.float32))  
 
#Initialize the variables  
init=tf.global_variables_initializer()  
 
#Start Training  
with tf.Session() as sess:  
    # Run the initializer  
    sess.run(init)  
    for step in range(1,training_steps+1):  
        batch_x,batch_y=mnist.train.next_batch(batch_size)  
        # Reshape data to get 28 seq of 28 elements  
        batch_x=batch_x.reshape((batch_size,timesteps,num_input))  
        #Run optimization op  
        sess.run(train_op,feed_dict={X:batch_x,Y:batch_y})  
        if step % display_step ==0 or step==1:  
            #Calculate batch loss and accuracy  
            loss,acc=sess.run([loss_op,accuracy],feed_dict={X:batch_x,Y:batch_y})  
            print('Step'+str(step)+" ,Minibatch Loss"+"{:.4f}".format(loss)+  
                  ",Training Accuracy="+"{:.3f}".format(acc))  
    print("Optimization Finished!")  
 
    #Calculate accuracy for 128 mnist test images  
    test_len=128  
    test_data=mnist.test.images[:test_len].reshape((-1,timesteps,num_input))  
    test_label=mnist.test.labels[:test_len]  
    print("Testing Accuracy:",sess.run(accuracy,feed_dict={X:test_data,Y:test_label}))  

 运行结果：