MNIST_run
来源：互联网 发布：java linux 文件权限 编辑：程序博客网 时间：2024/06/11 19:54
1.在这一节中我们将建立一个拥有一个线性层的softmax回归模型。
#导入Minst数据集 import input_data #导入名为‘input_data.py‘的input_data函数，这个函数是下载到本地并将数据存在命名为MNST的文件夹中 mnist = input_data.read_data_sets("MNST_data",one_hot=True) #导入tensorflow库 import tensorflow as tf #定义输入变量，把28*28的图片变成一维数组（丢失结构信息） x = tf.placeholder("float",[None,784]) #定义权重矩阵，把28*28=784的一维输入，变成0-9这10个数字的输出 w = tf.Variable(tf.zeros([784,10])) #偏置 b = tf.Variable(tf.zeros([10])) #核心运算，其实就是softmax（x*w+b） y = tf.nn.softmax(tf.matmul(x,w) + b) #这个是训练集的正确结果 y_ = tf.placeholder("float",[None,10]) #交叉熵，作为损失函数 cross_entropy = -tf.reduce_sum(y_ * tf.log(y)) #梯度下降算法，最小化交叉熵 train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy) #初始化，在run之前必须进行的 init = tf.global_variables_initializer() #创建session以便运算 sess = tf.Session() sess.run(init) #迭代1000次 for i in range(1000): #获取训练数据集的图片输入和正确表示数字 batch_xs, batch_ys = mnist.train.next_batch(100) #运行刚才建立的梯度下降算法，x赋值为图片输入，y_赋值为正确的表示数字 sess.run(train_step,feed_dict = {x:batch_xs, y_: batch_ys}) #tf.argmax获取最大值的索引。比较运算后的结果和本身结果是否相同。 #这步的结果应该是[1,1,1,1,1,1,1,1,0,1...........1,1,0,1]这种形式。 #1代表正确，0代表错误 correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1)) #tf.cast先将数据转换成float，防止求平均不准确。 #tf.reduce_mean由于只有一个参数，就是上面那个数组的平均值。 accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float")) #输出 print "test accuracy %g"%sess.run(accuracy,feed_dict={x:mnist.test.images,y_: mnist.test.labels}) 结果：
Extracting MNST_data/train-images-idx3-ubyte.gzExtracting MNST_data/train-labels-idx1-ubyte.gzExtracting MNST_data/t10k-images-idx3-ubyte.gzExtracting MNST_data/t10k-labels-idx1-ubyte.gztest accuracy 0.91582.在这一节，我们会将其扩展为一个拥有多层卷积网络的softmax回归模型。
# -*- coding: utf-8 -*- import tensorflow as tf#导入input_data用于自动下载和安装MNIST数据集import input_data mnist = input_data.read_data_sets("MNST_data",one_hot=True) #创建一个交互式Sessionsess = tf.InteractiveSession()#创建两个占位符，x为输入网络的图像，y_为输入网络的图像类别(0-9)这九个数字x = tf.placeholder("float", shape=[None, 784])y_ = tf.placeholder("float", shape=[None, 10])#权重初始化函数def weight_variable(shape): #输出服从截尾正态分布的随机值 initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial)#偏置初始化函数def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial)#创建卷积op#x 是一个4维张量，shape为[batch,height,width,channels]#卷积核移动步长为1。填充类型为SAME,可以不丢弃任何像素点def conv2d(x, W): return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding="SAME")#创建池化op#采用最大池化，也就是取窗口中的最大值作为结果#x 是一个4维张量，shape为[batch,height,width,channels]#ksize表示pool窗口大小为2x2,也就是高2，宽2#strides，表示在height和width维度上的步长都为2def 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，卷积层#初始化W为[5,5,1,32]的张量，表示卷积核大小为5*5，第一层网络的输入和输出神经元个数分别为1和32W_conv1 = weight_variable([5,5,1,32])#初始化b为[32],即输出大小b_conv1 = bias_variable([32])#把输入x(二维张量,shape为[batch, 784])变成4d的x_image，x_image的shape应该是[batch,28,28,1]#-1表示自动推测这个维度的sizex_image = tf.reshape(x, [-1,28,28,1])#把x_image和权重进行卷积，加上偏置项，然后应用ReLU激活函数，最后进行max_pooling#h_pool1的输出即为第一层网络输出，shape为[batch,14,14,1]h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1)#第2层，卷积层#卷积核大小依然是5*5，这层的输入和输出神经元个数为32和64W_conv2 = weight_variable([5,5,32,64])b_conv2 = weight_variable([64])#h_pool2即为第二层网络输出，shape为[batch,7,7,1]h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)h_pool2 = max_pool_2x2(h_conv2)#第3层, 全连接层#这层是拥有1024个神经元的全连接层#W的第1维size为7*7*64，7*7是h_pool2输出的size，64是第2层输出神经元个数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[batch, 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dropoutkeep_prob = tf.placeholder("float")h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)#输出层#最后，添加一个softmax层#可以理解为另一个全连接层，只不过输出时使用softmax将网络输出值转换成了概率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)#预测值和真实值之间的交叉墒cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))#train op, 使用ADAM优化器来做梯度下降。学习率为0.0001train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)#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_predict = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))#计算正确预测项的比例，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_predict, "float"))#初始化变量sess.run(tf.global_variables_initializer())#开始训练模型，循环20000次，每次随机从训练集中抓取50幅图像for i in range(20000): batch = 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[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})结果：
Extracting MNST_data/train-images-idx3-ubyte.gzExtracting MNST_data/train-labels-idx1-ubyte.gzExtracting MNST_data/t10k-images-idx3-ubyte.gzExtracting MNST_data/t10k-labels-idx1-ubyte.gzstep 0, training accuracy 0.12step 100, training accuracy 0.84step 200, training accuracy 0.92step 300, training accuracy 0.92step 400, training accuracy 0.98step 500, training accuracy 0.92step 600, training accuracy 0.98step 700, training accuracy 0.98step 800, training accuracy 0.9step 900, training accuracy 1step 1000, training accuracy 0.92step 1100, training accuracy 0.96step 1200, training accuracy 0.92step 1300, training accuracy 0.96step 1400, training accuracy 1step 1500, training accuracy 0.98step 1600, training accuracy 1step 1700, training accuracy 0.98step 1800, training accuracy 0.94step 1900, training accuracy 0.96step 2000, training accuracy 0.94step 2100, training accuracy 0.98step 2200, training accuracy 1step 2300, training accuracy 0.94step 2400, training accuracy 0.96step 2500, training accuracy 0.98step 2600, training accuracy 1step 2700, training accuracy 1step 2800, training accuracy 0.92step 2900, training accuracy 0.98step 3000, training accuracy 1step 3100, training accuracy 1step 3200, training accuracy 1step 3300, training accuracy 0.98step 3400, training accuracy 0.96step 3500, training accuracy 1step 3600, training accuracy 0.98step 3700, training accuracy 0.98step 3800, training accuracy 1step 3900, training accuracy 0.98step 4000, training accuracy 0.96step 4100, training accuracy 1step 4200, training accuracy 0.98step 4300, training accuracy 1step 4400, training accuracy 0.96step 4500, training accuracy 1step 4600, training accuracy 0.98step 4700, training accuracy 1step 4800, training accuracy 0.98step 4900, training accuracy 0.98step 5000, training accuracy 1step 5100, training accuracy 0.98step 5200, training accuracy 0.98step 5300, training accuracy 1step 5400, training accuracy 1step 5500, training accuracy 1step 5600, training accuracy 0.98step 5700, training accuracy 1step 5800, training accuracy 1step 5900, training accuracy 1step 6000, training accuracy 1step 6100, training accuracy 1step 6200, training accuracy 1step 6300, training accuracy 1step 6400, training accuracy 1step 6500, training accuracy 1step 6600, training accuracy 1step 6700, training accuracy 1step 6800, training accuracy 1step 6900, training accuracy 0.98step 7000, training accuracy 1step 7100, training accuracy 1step 7200, training accuracy 1step 7300, training accuracy 0.98step 7400, training accuracy 1step 7500, training accuracy 1step 7600, training accuracy 1step 7700, training accuracy 0.98step 7800, training accuracy 1step 7900, training accuracy 1step 8000, training accuracy 1step 8100, training accuracy 1step 8200, training accuracy 0.96step 8300, training accuracy 1step 8400, training accuracy 1step 8500, training accuracy 1step 8600, training accuracy 1step 8700, training accuracy 1step 8800, training accuracy 0.98step 8900, training accuracy 1step 9000, training accuracy 0.98step 9100, training accuracy 1step 9200, training accuracy 1step 9300, training accuracy 1step 9400, training accuracy 1step 9500, training accuracy 1step 9600, training accuracy 0.98step 9700, training accuracy 1step 9800, training accuracy 1step 9900, training accuracy 1step 10000, training accuracy 0.98step 10100, training accuracy 1step 10200, training accuracy 1step 10300, training accuracy 1step 10400, training accuracy 0.96step 10500, training accuracy 1step 10600, training accuracy 1step 10700, training accuracy 1step 10800, training accuracy 1step 10900, training accuracy 1step 11000, training accuracy 1step 11100, training accuracy 1step 11200, training accuracy 1step 11300, training accuracy 1step 11400, training accuracy 1step 11500, training accuracy 1step 11600, training accuracy 0.98step 11700, training accuracy 1step 11800, training accuracy 1step 11900, training accuracy 1step 12000, training accuracy 1step 12100, training accuracy 1step 12200, training accuracy 1step 12300, training accuracy 1step 12400, training accuracy 1step 12500, training accuracy 1step 12600, training accuracy 1step 12700, training accuracy 1step 12800, training accuracy 1step 12900, training accuracy 1step 13000, training accuracy 1step 13100, training accuracy 1step 13200, training accuracy 1step 13300, training accuracy 1step 13400, training accuracy 1step 13500, training accuracy 1step 13600, training accuracy 1step 13700, training accuracy 1step 13800, training accuracy 1step 13900, training accuracy 1step 14000, training accuracy 1step 14100, training accuracy 1step 14200, training accuracy 1step 14300, training accuracy 1step 14400, training accuracy 1step 14500, training accuracy 1step 14600, training accuracy 1step 14700, training accuracy 1step 14800, training accuracy 1step 14900, training accuracy 1step 15000, training accuracy 1step 15100, training accuracy 1step 15200, training accuracy 1step 15300, training accuracy 1step 15400, training accuracy 1step 15500, training accuracy 1step 15600, training accuracy 1step 15700, training accuracy 1step 15800, training accuracy 1step 15900, training accuracy 1step 16000, training accuracy 1step 16100, training accuracy 1step 16200, training accuracy 1step 16300, training accuracy 1step 16400, training accuracy 1step 16500, training accuracy 1step 16600, training accuracy 1step 16700, training accuracy 1step 16800, training accuracy 1step 16900, training accuracy 1step 17000, training accuracy 1step 17100, training accuracy 1step 17200, training accuracy 1step 17300, training accuracy 1step 17400, training accuracy 1step 17500, training accuracy 1step 17600, training accuracy 1step 17700, training accuracy 1step 17800, training accuracy 1step 17900, training accuracy 1step 18000, training accuracy 1step 18100, training accuracy 1step 18200, training accuracy 1step 18300, training accuracy 1step 18400, training accuracy 1step 18500, training accuracy 1step 18600, training accuracy 1step 18700, training accuracy 1step 18800, training accuracy 1step 18900, training accuracy 1step 19000, training accuracy 1step 19100, training accuracy 1step 19200, training accuracy 1step 19300, training accuracy 1step 19400, training accuracy 1step 19500, training accuracy 1step 19600, training accuracy 1step 19700, training accuracy 1step 19800, training accuracy 1step 19900, training accuracy 1test accuracy 0.991
