Mnist采用CNN代码
2016-07-19 11:04
190 查看
关于mnist的CNN方法的注释
import tensorflow as tf import input_data 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) def conv2d(x, W): return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') #这里的卷积使用的参数是padding='SAME',因此卷积完了之后图像大小不变 def max_pool_2x2(x): return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) sess = tf.InteractiveSession() x = tf.placeholder("float", shape=[None, 784]) y_ = tf.placeholder("float", shape=[None, 10]) #占位符 W = tf.Variable(tf.zeros([784,10])) b = tf.Variable(tf.zeros([10])) #用变量来表示模型参数W,b W_conv1 = weight_variable([5, 5, 1, 32]) b_conv1 = bias_variable([32]) #[5,5,1,32]前面两个维度是patch的大小,然后是输入通道数目,输出通道数目 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) 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) # Now image size is reduced to 7*7 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) W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv)) #计算交叉熵 train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) #使用ADAM的方法进行优化 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 %.3f"%(i, train_accuracy) train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5}) print "Training finished" print "test accuracy %.3f" % accuracy.eval(feed_dict={ x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})
相关文章推荐
- python 日志收集系统
- 《C++ 笔记》 Part5 C++ 资源大全中文版
- Java中Properties类的操作
- 静态块,代码块,构造方法的区别
- C++11新特性之新类型与初始化
- C# 托管资源和非托管资源
- 在学习java的路上
- 一条进程的栈区、堆区、数据区和代码区在内存中的映射
- 下面代码中,数组LA[ ]维度怎么就自动扩充了呢
- java 面向对象概念
- java基础-使用Arrays管理数组排序,复制,查找,填充
- Java中使用Collections.sort()方法对数字和字符串泛型的LIst进行排序
- 关于Java权限控制SecurityManager的理解
- eclipse发布web项目兼ssh框架搭建
- C语言getenv()函数:取得环境变量内容
- JAVA-MyBatis ORM
- import numpy 和 from numpy import * 的区别
- C#WinCE 记录日志文件
- ASP.NET MVC设计原则讲解
- SSM报错:java.sql.SQLException: 无效的列类型: 1111