TensorFlow入门02：cnn实现MNIST分类的源码及关键函数解析

该例程实现了cnn神经网络对MNIST的分类。其源码和解析如下：

#!/usr/bin/python2.7#coding:utf-8import input_datamnist = input_data.read_data_sets('MNIST_data',one_hot=True)import tensorflow as tfsess = tf.InteractiveSession()x = tf.placeholder("float", shape=[None, 784])y_ = tf.placeholder("float", shape=[None, 10])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)#卷积使用1步长（stride size），0边距（padding size）的模板#保证了输入和输出是同样的大小,需理解步长和边距该如何设置def conv2d(x, W):  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')#池化用简单传统的2x2大小的模板做max pooling#注意，池化后输出矩阵和输入矩阵的大小有所不同。#在本例中，28x28大小的矩阵池化后的大小为14x14def max_pool_2x2(x):  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],                        strides=[1, 2, 2, 1], padding='SAME')#第1层卷积#前2个参数时卷积的patch大小，第3个是输入的通道数目，第4个是输出的通道数目W_conv1 = weight_variable([5, 5, 1, 32])b_conv1 = bias_variable([32])#为了用这一层，将x变成一个4d向量,其第2、第3维对应图片的宽、高，最后一维代表图片的颜色通道数x_image = tf.reshape(x, [-1,28,28,1])#卷积与池化h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1)#第二层卷积#前2个参数时卷积的patch大小#第3个是输入的通道数目，由上一层的输出层个数决定#第4个是输出的通道数目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)#密集连接层 #经过两次2x2的池化，现在图片尺寸大小weight7*7，共有64个卷积图#我们加入一个有1024个神经元的全连接层，用于处理整个图片#问题？这里的W_fc1 = weight_variable([7 * 7 * 64, 1024])b_fc1 = bias_variable([1024])#并把池化层输出的张量reshape成一些向量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)#加入dropout来减少过拟合#用一个placeholder来代表一个神经元的输出在dropout中保持不变的概率#这样我们可以在训练过程中启用dropout，在测试过程中关闭dropoutkeep_prob = tf.placeholder("float")h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)#softmax输出层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)#训练和评估模型cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))#使用复杂的ADAM优化器来做梯度最速下降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"))#初始化variables型变量sess.run(tf.initialize_all_variables())for i in range(20000):  batch = mnist.train.next_batch(50)     if i%100 == 0:    #在feed_dict中加入额外的参数keep_prob来控制dropout比例    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})