TensorFlow中的CNN进行mnist手写数字代码_tensorflow cnn 手写数字-CSDN博客

此代码为使用TensorFlow中的CNN进行mnist手写数字代码，所有代码全部来自于TensorFlow官方教程，不过加入了我自己的理解和笔记，官方教程链接http://www.tensorfly.cn/tfdoc/api_docs/SOURCE/tutorials/mnist_pros.html，主要作用是作为自己的一个笔记，在以后忘记的时候回来看看，官网上面的准确率为99.2%，我的结果是99.3%

import tensorflow as tf
#导入mnist数据下载的TensorFlow源码
from tensorflow.examples.tutorials.mnist import input_data
#一个会话交互模式，后面不需要tf.Session()了
sess = tf.InteractiveSession()
# 导入数据
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

#输入样本和标签的占位符
x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])

#权重和偏置项初始化函数
def weight_variable(shape):
    #产生符合正态分布的随机权重
  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)

#卷积网络和最大池化层函数
def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')

#第一层卷积权重w和偏执项b，32指卷积核的数量
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

#输入
x_image = tf.reshape(x, [-1,28,28,1])
#relu激活函数
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#第二层卷积网络的权重w和偏执项b，32位上一层输出的通道数，64位这一层的卷积核数量
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)

#定义全连接层的权重w和偏执项b，7 * 7 * 64是两层卷积操作后的图片维度
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)
#dropout防止过拟合，随机扔掉keep_prob的权重连接
#dropout占位符
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
#softmax
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
#交叉熵
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
#权重更新算法
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
#计算准确率
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
#初始化变量
sess.run(tf.initialize_all_variables())
#训练及为占位符赋值
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    #accuracy.eval是由于前面的tf.InteractiveSession()，相当于sess.run(accuracy,feed_dict)
    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}))

最重要的就是要理解TensorFlow的operation图，它是基于图进行计算，需要先定义图，执行会话之后再赋值占位符进行计算。