TensorFlow学习二:MNIST机器学习入门
来源:互联网 发布:我的淘宝没有我要开店 编辑:程序博客网 时间:2024/05/16 04:39
"""建立MNIST网络.实现模型的预测/计算误差/训练等模式.1. 预测 - 建立模型做前向预测.2. 计算误差 - 用于计算误差的层.3. 训练 - 利用计算得到的梯度对模型进行优化."""import mnist.input_data #注意import路径,需要将tensorflow中mnist文件夹当前目录mnist = mnist.input_data.read_data_sets('MNIST_data', one_hot=True)print mnist.train.images.shape, mnist.validation.images.shape, mnist.test.images.shapeimport tensorflow as tfsess = tf.InteractiveSession()x = tf.placeholder('float', shape=[None, 784]) #输入y_ = tf.placeholder('float', shape=[None, 10]) #输出def weight_variable(shape): #用于初始化权重 initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial)def bias_variable(shape): #用于初始化偏置 initial = tf.constant(0.1, shape=shape) return tf.Variable(initial)def conv2d(x, W): #进行卷积操作, 步长,编辑等等都为默认值 return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')def max_pool_2x2(x): #进行池化降维,采用的默认设置 return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')W_conv1 = weight_variable([5, 5, 1, 32]) #第一个卷积层b_conv1 = bias_variable([32])x_image = tf.reshape(x, [-1,28,28,1]) #输入tensor:x_imageh_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1) #输出tensor: h_pool1W_conv12 = weight_variable([5, 5, 32, 32])b_conv12 = bias_variable([32])h_conv12 = tf.nn.relu(conv2d(h_pool1, W_conv12) + b_conv12)W_conv2 = weight_variable([5, 5, 32, 64])b_conv2 = bias_variable([64])h_conv2 = tf.nn.relu(conv2d(h_conv12, W_conv2) + b_conv2)h_pool2 = max_pool_2x2(h_conv2)W_fc1 = weight_variable([7 * 7 * 64, 1024])b_fc1 = bias_variable([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)keep_prob = tf.placeholder(tf.float32)h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)W_fc2 = weight_variable([1024, 10])b_fc2 = bias_variable([10])y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2cross_entropy = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=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, tf.float32))sess.run(tf.global_variables_initializer())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}))
阅读全文
0 0
- TensorFlow学习二:MNIST机器学习入门
- tensorflow MNIST机器学习入门
- tensorflow- MNIST机器学习入门
- tensorflow-MNIST机器学习入门
- <二>、TensorFlow之MNIST机器学习入门(1)
- Tensorflow MNIST机器学习入门 分类学习
- tensorflow学习(2)MNIST机器学习入门
- TensorFlow之MNIST机器学习入门
- Tensorflow教程-MNIST机器学习入门
- TensorFlow框架之MNIST机器学习入门
- Tensorflow学习笔记(二)MNIST入门
- TensorFlow学习笔记(二)MNIST入门
- TensorFlow学习笔记(二):快速理解Tutorial第一个例子-MNIST机器学习入门
- Tensorflow学习笔记(二)——MNIST机器学习入门
- 机器学习入门--MNIST(二)
- MNIST机器学习入门
- MNIST机器学习入门
- MNIST机器学习入门
- 02,Lua 程序块
- 我录制的《Java优雅编程之道》视频教程,已经发布了
- PostgreSQL
- 使用递归解决问题的一般思路
- CSS3:nth-child(x) 选择器
- TensorFlow学习二:MNIST机器学习入门
- JavaScript面向对象(1)——谈谈对象
- 测试信号屏蔽与解除并递达
- GetSafeHwnd 解释
- 嵌入式视频方案学习第十二篇——视频编码模块VENC 一般初始化过程
- 数据结构与算法-01(算法走起)
- Codeforces Round #418 (Div. 2)
- 【论文阅读】Neural Machine Translation By Jointly Learning To Align and Translate
- leetcode-49. Group Anagrams