Tensorflow 优化学习

# coding: utf-8

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

print("hello")

#载入数据集
mnist = input_data.read_data_sets("F:\\TensorflowProject\\MNIST_data",one_hot=True)

#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])
keep_prob = tf.placeholder(tf.float32)
lr = tf.Variable(0.001,dtype=tf.float32)

#创建一个神经网络
# W = tf.Variable(tf.zeros([784,10]))
# b = tf.Variable(tf.zeros([10]))
W1 = tf.Variable(tf.truncated_normal([784,500],stddev=0.1))
b1 = tf.Variable(tf.zeros([500])+0.1)
L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
L1_drop = tf.nn.dropout(L1,keep_prob)

#隐藏层1
W2 = tf.Variable(tf.truncated_normal([500,300],stddev=0.1))
b2 = tf.Variable(tf.zeros([300])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2)
L2_drop = tf.nn.dropout(L2,keep_prob)

#隐藏层2
W3 = tf.Variable(tf.truncated_normal([300,10],stddev=0.1))
b3 = tf.Variable(tf.zeros([10])+0.1)
#L3 = tf.nn.tanh(tf.matmul(L2_drop,W3)+b3)
#L3_drop = tf.nn.dropout(L3,keep_prob)
prediction = tf.nn.softmax(tf.matmul(L2_drop,W3)+b3)

#W4 = tf.Variable(tf.truncated_normal([1000,10],stddev=0.1))
#b4 = tf.Variable(tf.zeros([10])+0.1)
#prediction = tf.nn.softmax(tf.matmul(L3_drop,W4)+b4)

#二次代价函数
#loss = tf.reduce_mean(tf.square(y-prediction))
#交叉熵
#loss值最小的时候准确率最高
#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)
#训练
train_step = tf.train.AdamOptimizer(lr).minimize(loss)

#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(30):
　　　　sess.run(tf.assign(lr,0.001*(0.95 ** epoch)))
　　　　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,keep_prob:1.0})

　　　　#测试准确率
　　　　#test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
　　　　#train_acc = sess.run(accuracy,feed_dict={x:mnist.train.images,y:mnist.train.labels,keep_prob:1.0})
　　　　learning_rate = sess.run(lr)
　　　　test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
　　　　print("Iter: "+str(epoch)+" ,Testing Accuracy "+str(test_acc)+" Train : "+str(learning_rate))

####运行效果

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
Iter: 0  ,Testing Accuracy  0.9509    Train : 0.001
Iter: 1  ,Testing Accuracy  0.9622    Train : 0.00095
Iter: 2  ,Testing Accuracy  0.9669    Train : 0.0009025
Iter: 3  ,Testing Accuracy  0.9691    Train : 0.000857375
Iter: 4  ,Testing Accuracy  0.9725    Train : 0.000814506
Iter: 5  ,Testing Accuracy  0.9748    Train : 0.000773781
Iter: 6  ,Testing Accuracy  0.9752    Train : 0.000735092
Iter: 7  ,Testing Accuracy  0.9769    Train : 0.000698337
Iter: 8  ,Testing Accuracy  0.9778    Train : 0.00066342
Iter: 9  ,Testing Accuracy  0.9779    Train : 0.000630249
Iter: 10  ,Testing Accuracy  0.9777    Train : 0.000598737
Iter: 11  ,Testing Accuracy  0.9785    Train : 0.0005688
Iter: 12  ,Testing Accuracy  0.98    Train : 0.00054036
Iter: 13  ,Testing Accuracy  0.9798    Train : 0.000513342
Iter: 14  ,Testing Accuracy  0.9796    Train : 0.000487675
Iter: 15  ,Testing Accuracy  0.9801    Train : 0.000463291
Iter: 16  ,Testing Accuracy  0.9805    Train : 0.000440127
Iter: 17  ,Testing Accuracy  0.9803    Train : 0.00041812
Iter: 18  ,Testing Accuracy  0.9808    Train : 0.000397214
Iter: 19  ,Testing Accuracy  0.9799    Train : 0.000377354
Iter: 20  ,Testing Accuracy  0.9798    Train : 0.000358486
Iter: 21  ,Testing Accuracy  0.9802    Train : 0.000340562
Iter: 22  ,Testing Accuracy  0.9812    Train : 0.000323534
Iter: 23  ,Testing Accuracy  0.9813    Train : 0.000307357
Iter: 24  ,Testing Accuracy  0.9816    Train : 0.000291989
Iter: 25  ,Testing Accuracy  0.9798    Train : 0.00027739
Iter: 26  ,Testing Accuracy  0.9822    Train : 0.00026352
Iter: 27  ,Testing Accuracy  0.9816    Train : 0.000250344
Iter: 28  ,Testing Accuracy  0.9822    Train : 0.000237827
Iter: 29  ,Testing Accuracy  0.9811    Train : 0.000225936