Tensorflow递归神经网络学习练习

import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data

#载入数据集

mnist = input_data.read_data_sets("F:\TensorflowProject\MNIST_data",one_hot=True)

# 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28行

lstm_size = 100 #隐层单元

n_classes = 10 # 10个分类

batch_size = 50 #每批次50个样本

n_batch = mnist.train.num_examples // batch_size #计算一共有多少个批次

#这里的none表示第一个维度可以是任意的长度

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

#正确的标签

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

#初始化权值

weights = tf.Variable(tf.truncated_normal([lstm_size, n_classes], stddev=0.1))

#初始化偏置值

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基本CELL

#lstm_cell = tf.contrib.rnn.core_rnn_cell.BasicLSTMCell(lstm_size)

lstm_cell = rnn.BasicLSTMCell(lstm_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})

　　　　test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})

　　　　print ("Iter " + str(epoch) + ", Testing Accuracy= " + str(test_acc ))

#############运行结果

Extracting F:\TensorflowProject\MNIST_data\train-images-idx3-ubyte.gz
Extracting F:\TensorflowProject\MNIST_data\train-labels-idx1-ubyte.gz
Extracting F:\TensorflowProject\MNIST_data\t10k-images-idx3-ubyte.gz
Extracting F:\TensorflowProject\MNIST_data\t10k-labels-idx1-ubyte.gz
WARNING:tensorflow:From <ipython-input-5-efe314a2932e>:40: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:

Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.

See tf.nn.softmax_cross_entropy_with_logits_v2.

Iter 0, Testing Accuracy= 0.7372
Iter 1, Testing Accuracy= 0.8334
Iter 2, Testing Accuracy= 0.908
Iter 3, Testing Accuracy= 0.9182
Iter 4, Testing Accuracy= 0.9172
Iter 5, Testing Accuracy= 0.9266
##############第二次运行

Iter  0  ,Testing Accuracy= 0.744
Iter  1  ,Testing Accuracy= 0.8028
Iter  2  ,Testing Accuracy= 0.8803
Iter  3  ,Testing Accuracy= 0.9115
Iter  4  ,Testing Accuracy= 0.9262
Iter  5  ,Testing Accuracy= 0.9303