TensorFlow 学习
来源:互联网 发布:阿里云费用中心 提现 编辑:程序博客网 时间:2024/06/01 07:19
在 TensorFlow 学习 - MNIST 之 SoftMax Regression 实现(完整代码,拷贝可运行) 中详细讲解了利用TensorFlow 对MNIST数据集分类的过程,精度在91%左右。这一篇利用卷积神经网络改善模型。
同样的,本文先附上完整可运行的代码,再分段介绍。
from tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data/", one_hot=True)import tensorflow as tfdef weight_v(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial)def bias_v(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial)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')sess = tf.InteractiveSession()x = tf.placeholder(tf.float32, [None,784])y_ = tf.placeholder("float",[None,10])x_image = tf.reshape(x, [-1,28,28,1])# first levelW_conv1 = weight_v([5, 5, 1, 32])b_conv1 = bias_v([32])h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1)# second levelW_conv2 = weight_v([5, 5, 32, 64])b_conv2 = bias_v([64])h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)h_pool2 = max_pool_2x2(h_conv2)# lineW_fc1 = weight_v([7 * 7 * 64, 1024])b_fc1 = bias_v([1024])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)#dropoutkeep_prob = tf.placeholder("float")h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)#outputW_fc2 = weight_v([1024, 10])b_fc2 = bias_v([10])y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))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"))sess.run(tf.initialize_all_variables())for i in range(20000): batch = mnist.train.next_batch(50) if i%100 == 0: 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})
定义函数
def weight_v(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial)def bias_v(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial)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')
为方便起见,将shape等操作定义为函数。 分别代表权重,偏置,卷积(卷积的strides为1),池化(2 * 2) 的filter池化。
初始化操作
sess = tf.InteractiveSession()x = tf.placeholder(tf.float32, [None,784])y_ = tf.placeholder("float",[None,10])x_image = tf.reshape(x, [-1,28,28,1])
x 为原始的输入,y_ 为真实的标签,将初始的x(一个图像为例) reshape为 28 * 28 * 1 的图像。
卷积层
W_conv1 = weight_v([5, 5, 1, 32])b_conv1 = bias_v([32])
定义5*5 * 1(一个图像为例)的filter,指定32个特征。因为设置的padding = ‘SAME’, 卷积之后的维度不变。依旧是28 * 28 * 1。
激活函数:
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
池化层
h_pool1 = max_pool_2x2(h_conv1)
28 * 28 * 1 经由2 * 2 的filter 得到 14 * 14 * 1 的特征,此处选择max_pool。解释见 卷积神经网络 - 卷积池化
重复 卷积+ 激活+ 池化
W_conv2 = weight_v([5, 5, 32, 64])b_conv2 = bias_v([64])h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)h_pool2 = max_pool_2x2(h_conv2)
14 * 14 * 1 的特征经由 2* 2 的filter 得到 7 * 7 * 1 的特征
全连接
W_fc1 = weight_v([7 * 7 * 64, 1024])b_fc1 = bias_v([1024])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)
加入一个有1024个神经元的全连接层处理整个图片
Dropout
keep_prob = tf.placeholder("float")h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
为了减少过拟合,在输入层之前加入dropout,输出在dropout中保持不变的概率。
输出层
W_fc2 = weight_v([1024, 10])b_fc2 = bias_v([10])y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
利用softmax函数判别
训练评估
详细见 TensorFlow 学习 - MNIST 之 SoftMax Regression 实现(完整代码,拷贝可运行)
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))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"))sess.run(tf.initialize_all_variables())for i in range(20000): batch = mnist.train.next_batch(50) if i%100 == 0: 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})
结果输出
(part)
阅读全文
1 0
- TensorFlow 学习
- Tensorflow学习
- 学习tensorflow
- Tensorflow学习
- TensorFlow 学习
- TensorFlow 学习
- TensorFlow 学习
- TensorFlow 学习
- TensorFlow学习
- Tensorflow学习
- tensorflow学习
- tensorflow学习
- tensorflow学习
- TensorFlow 学习
- TensorFlow学习1--TensorFlow基本概念
- [TensorFlow] TensorFlow学习的方向
- TensorFlow学习笔记-1
- TensorFlow学习总结
- 纳税服务系统【系统、子系统首页】
- 获取对象类型信息+查看对象类型的结构+设置信息深度
- “玲珑杯”线上赛 Round #15 河南专场:D -- 咸鱼商店
- linux jenkins+gradle+svn 自动化部署android项目+自签名
- 实习随手记-注册表
- TensorFlow 学习
- PHP数组的遍历
- PHP教程之数据库操作类封装
- Maven spring mvc 配置
- eclipse的Git忽略某些不需要提交的文件
- wpf 画圆计算
- 几种在线学习方法的上限比较 part-3
- 【Unet】客户端同步GameObject 列表
- 面试题12解析-多线程之间的协调示例