tensorflow实战之 简单卷积神经网络
来源:互联网 发布:藤县网络电视 编辑:程序博客网 时间:2024/05/16 01:21
# -*- coding: utf-8 -*-
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets('MNIST_data/',one_hot = True )
sess = tf.InteractiveSession() # 后面可以直接对Session进行操作,不必sess.run
def weight_variable(shape): # 输入矩阵的尺寸,返回weight矩阵
initial = tf.truncated_normal(shape,stddev = 0.1) # 初始化的变量为截断的正态分布标准差为0.1
return tf.Variable(initial) # 用tf.Variable生成变量
def bias_variable(shape): # 根据输入矩阵, 返回初始的偏置向量, 偏置常数为0.1
initial = tf.constant(0.1,shape = shape ) # 用tf.constant生成该维度的常数矩阵
return tf.Variable(initial)
def conv2d(x, w): # 输入两个矩阵返回其卷积结果
return tf.nn.conv2d(x,w, strides = [1,1,1,1], padding = 'SAME') # 用tf.nn.conv2d计算卷积
def max_pool_2x2(x): #池化函数 其中参数ksize为核函数的大小, strides 是移动步长,
#padiing参数有两个可选值其中same是去除两端相同值,valid是去除最右端
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_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}))
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets('MNIST_data/',one_hot = True )
sess = tf.InteractiveSession() # 后面可以直接对Session进行操作,不必sess.run
def weight_variable(shape): # 输入矩阵的尺寸,返回weight矩阵
initial = tf.truncated_normal(shape,stddev = 0.1) # 初始化的变量为截断的正态分布标准差为0.1
return tf.Variable(initial) # 用tf.Variable生成变量
def bias_variable(shape): # 根据输入矩阵, 返回初始的偏置向量, 偏置常数为0.1
initial = tf.constant(0.1,shape = shape ) # 用tf.constant生成该维度的常数矩阵
return tf.Variable(initial)
def conv2d(x, w): # 输入两个矩阵返回其卷积结果
return tf.nn.conv2d(x,w, strides = [1,1,1,1], padding = 'SAME') # 用tf.nn.conv2d计算卷积
def max_pool_2x2(x): #池化函数 其中参数ksize为核函数的大小, strides 是移动步长,
#padiing参数有两个可选值其中same是去除两端相同值,valid是去除最右端
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_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实战之 简单卷积神经网络
- [action]tensorflow深度学习实战 (4) 实现简单卷积神经网络
- Tensorflow深度学习之二:简单卷积神经网络CNN
- tensorflow之简单卷积神经网络(CNN)搭建
- 卷积神经网络之tensorflow实现
- Tensorflow中卷积神经网络之卷积层
- Tensorflow实战学习(二十七)【卷积神经网络】
- 《tensorflow实战》学习3——实现简单的卷积神经网络
- 使用tensorflow构建简单卷积神经网络
- 使用tensorflow构建简单卷积神经网络
- TensorFlow实现卷积神经网络(简单)
- tensorflow实现简单的卷积神经网络
- 简单卷积神经网络的tensorflow实现
- Tensorflow实例:实现简单的卷积神经网络
- tensorflow32《TensorFlow实战》笔记-05 TensorFlow实现卷积神经网络 code
- TensorFlow 之卷积神经网络一般过程
- TensorFlow 卷积神经网络之猫狗识别
- TensorFlow实战:Chapter-3(CNN-1-卷积神经网络简介)
- ios runtime 之消息发送机制三次拯救机会
- 为什么有些mp4不能在html5中video标签播放
- SQL2008安装重启失败解决方法
- maven报错问题
- 用Python从零开始创建区块链
- tensorflow实战之 简单卷积神经网络
- Java并发编程:线程池的使用
- Spring MVC之@RequestBody, @ResponseBody 详解
- java程序调用c# webservice
- 微信小程序图片显示
- js的函数定义
- 雷军如何靠条件概率逆袭?
- Java
- 国内可访问GPG Keyserver列表