TensorFlow基础笔记(2) minist分类学习

(1) 最简单的神经网络分类器

# encoding: UTF-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data as mnist_data
print("Tensorflow version " + tf.__version__)
print(tf.__path__)

tf.set_random_seed(0)

# 输入mnist数据
mnist = mnist_data.read_data_sets("data", one_hot=True)

#输入数据
x = tf.placeholder("float", [None, 784])
y_ = tf.placeholder("float", [None,10])

#权值输入
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
#神经网络输出
y = tf.nn.softmax(tf.matmul(x,W) + b)

#设置交叉熵
cross_entropy = -tf.reduce_sum(y_*tf.log(y))

#设置训练模型
learningRate = 0.005
train_step = tf.train.GradientDescentOptimizer(learningRate).minimize(cross_entropy)

init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

itnum = 1000;
batch_size = 100;
for i in range(itnum):
    print("the index " + str(i + 1) + " train")
    batch_xs, batch_ys = mnist.train.next_batch(batch_size)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})

 (2) 单层Softmax分类器与CNN多层分类器

#coding=utf-8

#mnist程序实现与优化
#author: maddock
#date: 2017.9.26
#reference:
#http://www.tensorfly.cn/tfdoc/tutorials/mnist_pros.html
#http://www.cnblogs.com/shihuc/p/6648130.html
#http://blog.csdn.net/wspba/article/details/54311566（mnist数据解析）
#http://blog.csdn.net/daska110/article/details/71630135 TensorFlow入门+MNIST运行的理解


import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data as mnist_data
print("Tensorflow version " + tf.__version__)
print(tf.__path__)

tf.set_random_seed(0)

# 输入mnist数据
mnist = mnist_data.read_data_sets("data", one_hot=True)

sess = tf.InteractiveSession()

##############################################################################################
print("构建Softmax 回归模型 ")
print("train num: ", mnist.train.images.shape[0]," image size ", mnist.train.images.shape[1])
print("test num: ", mnist.test.images.shape[0]," image size ", mnist.test.images.shape[1])

#这里的x和y并不是特定的值，相反，他们都只是一个占位符，可以在TensorFlow运行某一计算时根据该占位符输入具体的值。
x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))


sess.run(tf.global_variables_initializer())
y = tf.nn.softmax(tf.matmul(x,W) + b)
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

#每一步迭代，我们都会加载50个训练样本，然后执行一次train_step，并通过feed_dict将x 和 y_张量占位符用训练训练数据替代。
for i in range(1000):
    batch = mnist.train.next_batch(50)
    train_step.run(feed_dict={x: batch[0], y_: batch[1]})

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("max test accuracy: ",accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))


###########################################################################
print("
构建一个多层卷积网络")

def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)

#http://blog.csdn.net/mao_xiao_feng/article/details/78004522
def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

#http://blog.csdn.net/mao_xiao_feng/article/details/53453926
def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')


#设置第一层的权值
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
#把输入数据变成与w矩阵同纬度的矩阵
x_image = tf.reshape(x, [-1,28,28,1])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#设置第二层的权值
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

#设置全连接层1的权值
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#设置全连接层2的权值
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

#输出预测的分类
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run(tf.initialize_all_variables())
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    train_accuracy = accuracy.eval(feed_dict={
        x:batch[0], y_: batch[1], keep_prob: 1.0})
    print ("step %d, training accuracy %g"%(i, train_accuracy))
  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

print ("test accuracy %g"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

参考 http://www.tensorfly.cn/tfdoc/tutorials/mnist_pros.html

http://blog.csdn.net/mpk_no1/article/details/72855977 （结构不错）