1、介绍
MNIST是一个入门级的计算机视觉数据集,它包含各种手写数字图片。当我们开始学习编程的时候,第一件事往往是学习打印”Hello World”。而MNIST就是机器学习的”Hello World”
tensorflow官方教程,代码也是出自这里
2、代码
2.1 单层MNIST测试
#coding:utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#读取数据,直接用教程的代码读数据出错,将mnist数据下载到MNIST_data文件夹下
mnist = input_data.read_data_sets("MNIST_data/",one_hot=True)
#创建占位符并对权重与偏移进行初始化;输入图像尺寸是28*28=784,shape中None表示第一维为任意长度,输出为10个数
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]))
y = tf.nn.softmax(tf.matmul(x,w)+b)
#损失函数为交叉熵
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
#训练模型,采用梯度下降法训练
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
#创建交互式Session并初始化
sess = tf.InteractiveSession()
sess.run(tf.initialize_all_variables())
#每次从训练样本集中取100个batch进行训练
for i in range(1000):
batch_xs,batch_ys = mnist.train.next_batch(100)
sess.run(train_step,feed_dict={x:batch_xs,y_:batch_ys})
#评估模型,tf.argmax能给出某个tensor对象在某一维上数据最大值的索引。因为标签是由0,1组成了one-hot vector,返回的索引就是数值为1的位置
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
#因为tf.equal返回的是布尔值,使用tf.cast把布尔值转换成浮点数,然后用tf.reduce_mean求平均值
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
print sess.run(accuracy,feed_dict={x:mnist.test.images,y_:mnist.test.labels})
测试集打印的准确率大概为91%
2.2 多层卷积网络MNIST测试
#coding:utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
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])
#权重与偏移初始化函数
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)
#定义卷积与池化,卷积使用1步长,池化使用2x2的max pooling
#填充类型为SAME,输出尺寸=输入尺寸\移动步长的上限整数
#x是一个4维张量,shape为[batch,height,width,channels]
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1层卷积
#卷积核batch为5*5,输出特征为32,第三维对应输入的通道数
#第一层卷积输出为[-1,28,28,32],池化层输出[-1,14,14,32]
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
#把输入x变成4d向量
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)
#第2层卷积
#卷积核大小依然是5*5,上一层的输出作为这层的输入
#第二层卷积输出为[-1,14,14,64],池化层输出[-1,7,7,64]
W_conv2 = weight_variable([5,5,32,64])
b_conv2 = weight_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
#全连接层
#这层是拥有1024个神经元的全连接层,这层的输入为[-1,7,7,64]
#全连接层输出为[-1,1024]
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
#计算前需要把第2层的输出reshape成[-1, 7*7*64]的张量
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)
#Dropout层
#为了减少过拟合,在输出层前加入dropout,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)
#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)
#接下来就是训练和评估模型,训练时的优化方法为adam
cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_predict = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_predict, "float"))
sess.run(tf.initialize_all_variables())
for i in range(20000):
batch_x,batch_y = mnist.train.next_batch(50)
if i%100 == 0:
#每100次输出一次日志
train_accuracy = accuracy.eval(feed_dict={
x:batch_x, y_:batch_y, keep_prob:1.0})
print "step %d, training accuracy %g" % (i, train_accuracy)
train_step.run(feed_dict={x:batch_x, y_:batch_y, keep_prob:0.5})
print "test accuracy %g" % accuracy.eval(feed_dict={
x:mnist.test.images, y_:mnist.test.labels, keep_prob:1.0})