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-8
import input_data
mnist = input_data.read_data_sets('MNIST_data',one_hot=True)
import tensorflow as tf
sess = 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14x14
def 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dropout
keep_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})