[TensorFlow实战] 简单CNN
来源:互联网 发布:青岛seo外包公司费用 编辑:程序博客网 时间:2024/05/18 02:35
代码
import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datadataset_default_path = r'C:\Users\Administrator\.keras\datasets'mnist = input_data.read_data_sets(dataset_default_path,one_hot=True)sess = tf.InteractiveSession()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)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')x = tf.placeholder(tf.float32,[None,784])y_ = tf.placeholder(tf.float32,[None,10])x_image = tf.reshape(x,[-1,28,28,1])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)h_pool1 = max_pool_2x2(h_conv1)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)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.nn.softmax(tf.matmul(h_fc1_drop,w_fc2)+b_fc2)cross_entropy = tf.reduce_mean( -tf.reduce_sum(y_*tf.log(y_conv),reduction_indices=[1]))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))tf.global_variables_initializer().run()for i in range(20000): batch = mnist.train.next_batch(50) if i%100 == 0 : train_acc = accuracy.eval({x:batch[0],y_:batch[1],keep_prob:1.0}) print("iter %d, acc:%g" %(i,train_acc)) train_step.run(feed_dict={x:batch[0],y_:batch[1],keep_prob:0.5})print(accuracy.eval({x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))
阅读全文
0 0
- [TensorFlow实战] 简单CNN
- Tensorflow简单CNN实现
- TensorFlow实战——CNN
- TensorFlow实战(三)CNN
- TensorFlow笔记之简单cnn
- Tensorflow CNN 的简单实现
- Tensorflow实战-CNN网络Mnist识别
- 基于Tensorflow的CNN简单实现
- tensorflow程序-最简单的CNN模型
- windows下使用tensorflow简单实现CNN
- 简单实现Tensorflow CNN图像训练
- TensorFlow(0.12.0) LeNet-2 CNN实战问题分析
- TensorFlow实战——CNN(Inception-v3)
- TensorFlow实战:Chapter-3(CNN-1-卷积神经网络简介)
- 《tensorflow 实战》学习4——AlexNet(经典CNN)
- tensorflow实战2:实现mnist 单层cnn分类
- TensorFlow实战:Mask R-CNN介绍与实现,instance segmention
- Tensorflow中的CNN layer参数(即用tensorflow框架实现简单CNN)
- 高速通道部署实践:跨地域云上私网互通
- amaze ui包中缺少jquery文件解决办法
- Android 线程池的使用
- 持续集成之⑤:jenkins结合脚本实现代码自动化部署及一键回滚至上一版本
- vue2.0构建单页应用最佳实战案例 vue.js
- [TensorFlow实战] 简单CNN
- 目录与文件的权限意义
- C#继承
- 【学习笔记】nodejs操作mysql增删改查
- dubbo+zoopkeeper入门详解
- Unity5.4 WWW频繁加载崩溃问题 Fatal signal 11 (SIGSEGV) at 0x00000004 (code=1)
- 改数据库表类型
- 通过 SSH 端口转发实现异地内网服务器互通
- HTML5之HSLA colors