长短时记忆网络LSTM

长短时记忆网络LSTM
知识我还为完全搞…之后用到再学一遍

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets('MNIST_data',one_hot=True)
tf.reset_default_graph()
# 输入图片是28*28
n_inputs = 28 # 输入一行，一行有28个数据
max_time = 28 # 一共有28行
lstm_size = 100 # 隐层单元
n_classes = 10 # 10个分类
batch_size = 64 # 每批次50个样本
n_batch=mnist.train.num_examples//batch_size

#定义两个placeholder
x=tf.placeholder(tf.float32,[None,784])#28*28
y=tf.placeholder(tf.float32,[None,10])

#输出层的权值和偏置
#初始化权值 lstm_size = 100,n_class = 10,lstm网络有100个输出，输出层有10个输出
weights = tf.Variable(tf.truncated_normal([lstm_size,n_classes],stddev = 0.1))
#初始化偏置
biases = tf.Variable(tf.constant(0.1,shape = [n_classes]))

# 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，设置block的个数
    lstm_cell = tf.nn.rnn_cell.LSTMCell(lstm_size)
    # final_state[state,batch_size,cell.state_size]
    # 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


#计算输出
prediction=RNN(x,weights,biases)
#交叉熵代价函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
#使用AdamOptimizer进行优化
train_step=tf.train.AdamOptimizer(0.0001).minimize(loss)
#结果存放在一个布尔型列表中
correct_prediction=tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))#argmax返回一维张量中最大的值的下标
#计算准确率
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
# 初始化
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(11):
        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))

运行结果
Iter0,Testing Accuracy=0.7103
Iter1,Testing Accuracy=0.8392
Iter2,Testing Accuracy=0.8796
Iter3,Testing Accuracy=0.9078
Iter4,Testing Accuracy=0.921
Iter5,Testing Accuracy=0.9287
Iter6,Testing Accuracy=0.9388
Iter7,Testing Accuracy=0.9385
Iter8,Testing Accuracy=0.9473
Iter9,Testing Accuracy=0.9455
Iter10,Testing Accuracy=0.9515