Tensorflow学习——AdamOptimizer

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\#每个批次的⼤⼩，训练时⼀次100张放⼊神经⽹络中训练batch_size = 100

#计算⼀共有多少个批次

n_batch = mnist.train.num_examples//batch_size#定义两个placeholder

x = tf.placeholder(tf.float32,[None,784])#0-9⼗个数字

y = tf.placeholder(tf.float32,[None,10])#创建⼀个神经⽹络

W = tf.Variable(tf.zeros([784,10]))b = tf.Variable(tf.zeros([10]))

prediction = tf.nn.softmax(tf.matmul(x,W)+b)

#⼆次代价函数

#loss = tf.reduce_mean(tf.square(y-prediction))#交叉熵代价函数

#使⽤交叉熵定义代价函数，可以加快模型收敛速度

#loss = tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction)

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))#使⽤梯度下降法

#train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)train_step = tf.train.AdamOptimizer(0.01).minimize(loss) #1e-2#初始化变量

init = tf.global_variables_initializer()

#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))#求准确率

accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))#

with tf.Session() as sess:　　sess.run(init)

　　for epoch in range(21):

　　　　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})

　　　　#测试准确率

　　　　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

Extracting F:\\TensorflowProject\\MNIST_data\rain-images-idx3-ubyte.gzExtracting F:\\TensorflowProject\\MNIST_data\rain-labels-idx1-ubyte.gzExtracting F:\\TensorflowProject\\MNIST_data\10k-images-idx3-ubyte.gzExtracting F:\\TensorflowProject\\MNIST_data\10k-labels-idx1-ubyte.gzIter: 0 ,Testing Accuracy 0.9221Iter: 1 ,Testing Accuracy 0.9133Iter: 2 ,Testing Accuracy 0.9271Iter: 3 ,Testing Accuracy 0.9262Iter: 4 ,Testing Accuracy 0.9299Iter: 5 ,Testing Accuracy 0.9293Iter: 6 ,Testing Accuracy 0.9301Iter: 7 ,Testing Accuracy 0.9299Iter: 8 ,Testing Accuracy 0.9287

Iter: 9 ,Testing Accuracy 0.9319Iter: 10 ,Testing Accuracy 0.9317Iter: 11 ,Testing Accuracy 0.9315Iter: 12 ,Testing Accuracy 0.9307Iter: 13 ,Testing Accuracy 0.932Iter: 14 ,Testing Accuracy 0.9314Iter: 15 ,Testing Accuracy 0.9316Iter: 16 ,Testing Accuracy 0.9311Iter: 17 ,Testing Accuracy 0.9333Iter: 18 ,Testing Accuracy 0.9318Iter: 19 ,Testing Accuracy 0.9318Iter: 20 ,Testing Accuracy 0.9289