tensorflow学习笔记五:mnist实例--卷积神经网络(CNN)
mnist的卷積神經(jīng)網(wǎng)絡(luò)例子和上一篇博文中的神經(jīng)網(wǎng)絡(luò)例子大部分是相同的。但是CNN層數(shù)要多一些,網(wǎng)絡(luò)模型需要自己來構(gòu)建。
程序比較復(fù)雜,我就分成幾個(gè)部分來敘述。
首先,下載并加載數(shù)據(jù):
import tensorflow as tf import tensorflow.examples.tutorials.mnist.input_data as input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) #下載并加載mnist數(shù)據(jù) x = tf.placeholder(tf.float32, [None, 784]) #輸入的數(shù)據(jù)占位符 y_actual = tf.placeholder(tf.float32, shape=[None, 10]) #輸入的標(biāo)簽占位符定義四個(gè)函數(shù),分別用于初始化權(quán)值W,初始化偏置項(xiàng)b, 構(gòu)建卷積層和構(gòu)建池化層。?
#定義一個(gè)函數(shù),用于初始化所有的權(quán)值 W def weight_variable(shape):initial = tf.truncated_normal(shape, stddev=0.1)return tf.Variable(initial)#定義一個(gè)函數(shù),用于初始化所有的偏置項(xiàng) b def bias_variable(shape):initial = tf.constant(0.1, shape=shape)return tf.Variable(initial)#定義一個(gè)函數(shù),用于構(gòu)建卷積層 def conv2d(x, W):return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')#定義一個(gè)函數(shù),用于構(gòu)建池化層 def max_pool(x):return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')接下來構(gòu)建網(wǎng)絡(luò)。整個(gè)網(wǎng)絡(luò)由兩個(gè)卷積層(包含激活層和池化層),一個(gè)全連接層,一個(gè)dropout層和一個(gè)softmax層組成。?
#構(gòu)建網(wǎng)絡(luò) x_image = tf.reshape(x, [-1,28,28,1]) #轉(zhuǎn)換輸入數(shù)據(jù)shape,以便于用于網(wǎng)絡(luò)中 W_conv1 = weight_variable([5, 5, 1, 32]) b_conv1 = bias_variable([32]) h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) #第一個(gè)卷積層 h_pool1 = max_pool(h_conv1) #第一個(gè)池化層 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) #第二個(gè)卷積層 h_pool2 = max_pool(h_conv2) #第二個(gè)池化層 W_fc1 = weight_variable([7 * 7 * 64, 1024]) b_fc1 = bias_variable([1024]) h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64]) #reshape成向量 h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) #第一個(gè)全連接層 keep_prob = tf.placeholder("float") h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) #dropout層 W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_predict=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) #softmax層網(wǎng)絡(luò)構(gòu)建好后,就可以開始訓(xùn)練了。
cross_entropy = -tf.reduce_sum(y_actual*tf.log(y_predict)) #交叉熵 train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy) #梯度下降法 correct_prediction = tf.equal(tf.argmax(y_predict,1), tf.argmax(y_actual,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) #精確度計(jì)算 sess=tf.InteractiveSession() sess.run(tf.initialize_all_variables()) for i in range(20000):batch = mnist.train.next_batch(50)if i%100 == 0: #訓(xùn)練100次,驗(yàn)證一次train_acc = accuracy.eval(feed_dict={x:batch[0], y_actual: batch[1], keep_prob: 1.0})print 'step %d, training accuracy %g'%(i,train_acc)train_step.run(feed_dict={x: batch[0], y_actual: batch[1], keep_prob: 0.5})test_acc=accuracy.eval(feed_dict={x: mnist.test.images, y_actual: mnist.test.labels, keep_prob: 1.0}) print "test accuracy %g"%test_accTensorflow依賴于一個(gè)高效的C++后端來進(jìn)行計(jì)算。與后端的這個(gè)連接叫做session。一般而言,使用TensorFlow程序的流程是先創(chuàng)建一個(gè)圖,然后在session中啟動(dòng)它。
這里,我們使用更加方便的InteractiveSession類。通過它,你可以更加靈活地構(gòu)建你的代碼。它能讓你在運(yùn)行圖的時(shí)候,插入一些計(jì)算圖,這些計(jì)算圖是由某些操作(operations)構(gòu)成的。這對(duì)于工作在交互式環(huán)境中的人們來說非常便利,比如使用IPython。
訓(xùn)練20000次后,再進(jìn)行測試,測試精度可以達(dá)到99%。
完整代碼:
# -*- coding: utf-8 -*- """ Created on Thu Sep 8 15:29:48 2016@author: root """ import tensorflow as tf import tensorflow.examples.tutorials.mnist.input_data as input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) #下載并加載mnist數(shù)據(jù) x = tf.placeholder(tf.float32, [None, 784]) #輸入的數(shù)據(jù)占位符 y_actual = tf.placeholder(tf.float32, shape=[None, 10]) #輸入的標(biāo)簽占位符#定義一個(gè)函數(shù),用于初始化所有的權(quán)值 W def weight_variable(shape):initial = tf.truncated_normal(shape, stddev=0.1)return tf.Variable(initial)#定義一個(gè)函數(shù),用于初始化所有的偏置項(xiàng) b def bias_variable(shape):initial = tf.constant(0.1, shape=shape)return tf.Variable(initial)#定義一個(gè)函數(shù),用于構(gòu)建卷積層 def conv2d(x, W):return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')#定義一個(gè)函數(shù),用于構(gòu)建池化層 def max_pool(x):return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')#構(gòu)建網(wǎng)絡(luò) x_image = tf.reshape(x, [-1,28,28,1]) #轉(zhuǎn)換輸入數(shù)據(jù)shape,以便于用于網(wǎng)絡(luò)中 W_conv1 = weight_variable([5, 5, 1, 32]) b_conv1 = bias_variable([32]) h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) #第一個(gè)卷積層 h_pool1 = max_pool(h_conv1) #第一個(gè)池化層 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) #第二個(gè)卷積層 h_pool2 = max_pool(h_conv2) #第二個(gè)池化層 W_fc1 = weight_variable([7 * 7 * 64, 1024]) b_fc1 = bias_variable([1024]) h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64]) #reshape成向量 h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) #第一個(gè)全連接層 keep_prob = tf.placeholder("float") h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) #dropout層 W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_predict=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) #softmax層 cross_entropy = -tf.reduce_sum(y_actual*tf.log(y_predict)) #交叉熵 train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy) #梯度下降法 correct_prediction = tf.equal(tf.argmax(y_predict,1), tf.argmax(y_actual,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) #精確度計(jì)算 sess=tf.InteractiveSession() sess.run(tf.initialize_all_variables()) for i in range(20000):batch = mnist.train.next_batch(50)if i%100 == 0: #訓(xùn)練100次,驗(yàn)證一次train_acc = accuracy.eval(feed_dict={x:batch[0], y_actual: batch[1], keep_prob: 1.0})print('step',i,'training accuracy',train_acc)train_step.run(feed_dict={x: batch[0], y_actual: batch[1], keep_prob: 0.5})test_acc=accuracy.eval(feed_dict={x: mnist.test.images, y_actual: mnist.test.labels, keep_prob: 1.0}) print("test accuracy",test_acc) View Code?
轉(zhuǎn)載于:https://www.cnblogs.com/denny402/p/5853538.html
總結(jié)
以上是生活随笔為你收集整理的tensorflow学习笔记五:mnist实例--卷积神经网络(CNN)的全部內(nèi)容,希望文章能夠幫你解決所遇到的問題。
- 上一篇: 搭建Python+Django开发环境
- 下一篇: 信息表示和处理 from compu