TensorFlow | 使用Tensorflow带你实现MNIST手写字体识别

2024-06-05 19:48
文章标签 实现 使用 字体 手写 识别 mnist tensorflow

本文主要是介绍TensorFlow | 使用Tensorflow带你实现MNIST手写字体识别，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

github：https://github.com/MichaelBeechan
CSDN：https://blog.csdn.net/u011344545

涉及代码：https://github.com/MichaelBeechan/Learning_TensorFlow-Kaggle_MNIST 欢迎Fork和Star

Learning_TensorFlow-Kaggle_MNIS

一步步带你通过项目（MNIST手写识别）学习入门TensorFlow以及神经网络的知识

**

TF_Variable：TensorFlow入门

**

# -*- coding:utf-8 -*-
"""
Name: Michael Beechan
School: Chongqing University of Technology
Time: 2018.10.4
Description: tensorflow变量初始化
https://baike.baidu.com/item/TensorFlow/18828108?fr=aladdin
"""
import tensorflow as tf
# 变量定义
w = tf.Variable([[0.5, 1.0]])
x = tf.Variable([[2.0], [1.0]])
# 矩阵乘法
y = tf.matmul(w, x)
print(y)# 函数
norm = tf.random_normal([2, 3], mean = -1, stddev = 4)
c = tf.constant([[1, 2], [3, 4], [5, 6]])
shuff = tf.random_shuffle(c)  # shuffle洗牌
sess = tf.Session()
print(sess.run(norm))
print(sess.run(shuff))
# 将numpy的一些数据转换为tensorflow能用的类型
import numpy as np
a = np.zeros((3, 3))
ta = tf.convert_to_tensor(a)
print(sess.run(ta))# 创建一个变量 并用for循环对变量进行赋值操作
num  =tf.Variable(0, name="count")
new_value = tf.add(num, 10)
op = tf.assign(num, new_value)
print(op)
# 初始化全局变量
init_op = tf.global_variables_initializer()
# 定义运行会话
with tf.Session() as sess:sess.run(init_op)print(sess.run(num))for i in range(5):sess.run(op)print(sess.run(num))# 通过feed设置placeholder的值
# 声明变量是不赋值，计算时进行赋值  使用feed
input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
value_new = tf.multiply(input1, input2)with tf.Session() as sess:print(sess.run(value_new, feed_dict={input1:23.0, input2:11.0}))

**

Kaggle_mnist

**
使用softMax作为激活函数，交叉熵做损失函数，梯度下降法优化的单层神经网络学习识别
准确率：88%左右

#-*- coding:utf-8 -*-
"""
Name: Michael Beechan
School: Chongqing University of Technology
Time: 2018.10.4
Description: Kaggle MINIST 手写图片识别  Digit Recognizer
http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/mnist_beginners.html
"""
"""
一、数据的准备
二、模型的设计
三、代码实现
28*28 = 784 的二维数组
训练数据和测试数据，都可以分别转化为[42000,769]和[28000,768]的数组
模型建立：
1）使用一个最简单的单层的神经网络进行学习
2）用SoftMax来做为激活函数
3）用交叉熵来做损失函数
4）用梯度下降来做优化方式
"""#88.45% 识别正确率
import pandas as pd
import numpy as np
import tensorflow as tf#加载数据
train = pd.read_csv("train.csv")
images = train.iloc[:, 1:].values
#labels_flat = train[[0]].values.ravel()
labels_flat = train.iloc[:, 0].values.ravel()#输入处理
images = images.astype(np.float)
images = np.multiply(images, 1.0 / 255.0)
print("输入数据的数量：(%g, %g)" % images.shape)
images_size = images.shape[1]
images_width = images_height = np.ceil(np.sqrt(images_size)).astype(np.uint8)
print("图片的长 = {0}\n图片的高 = {1}".format(images_width, images_height))x = tf.placeholder('float', shape=[None, images_size])#结果处理
labels_count = np.unique(labels_flat).shape[0]
print('结果的种类 = {0}'.format(labels_count))
y = tf.placeholder('float', shape=[None, labels_count])#One-Hot编码 :离散特征处理——独热编码  scikit_learn有封装了现成的编码函数OneHotEncoder()
def dense_to_one_hot(labels_dense, num_calsses):num_labels = labels_dense.shape[0]index_offset = np.arange(num_labels) * num_calsseslabels_one_hot = np.zeros((num_labels, num_calsses))#flat返回的是一个迭代器labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1return labels_one_hotlabels = dense_to_one_hot(labels_flat, labels_count)
labels = labels.astype(np.uint8)
print('结果的数量：({0[0]}, {0[1]})'.format(labels.shape))#数据划分
VALIDATION_SIZE = 2000validation_images = images[:VALIDATION_SIZE]
validation_labels = labels[:VALIDATION_SIZE]train_images = images[VALIDATION_SIZE:]
train_labels = labels[VALIDATION_SIZE:]batch_size = 100
n_batch = len(train_images)//batch_size#建立神经网络
weight = tf.Variable(tf.zeros([784, 10]))
biases = tf.Variable(tf.zeros([10]))
result = tf.matmul(x, weight) + biases
prediction = tf.nn.softmax(result)loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y, logits=prediction))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)init = tf.global_variables_initializer()correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))with tf.Session() as sess:sess.run(init)for epoch in range(50):for batch in range(n_batch):batch_x = train_images[batch * batch_size:(batch+1) * batch_size]batch_y = train_labels[batch * batch_size:(batch+1) * batch_size]sess.run(train_step, feed_dict={x:batch_x, y:batch_y})accuracy_n = sess.run(accuracy, feed_dict={x:validation_images, y:validation_labels})print("第"+str(epoch+1)+"轮，准确度为：" + str(accuracy_n))```**

CNN_mnist

卷积神经网络——卷积层1+池化层1+卷积层2+池化层2+全连接1+Dropout层+输出层
准确率：训练20 accuracy is 0.984

#-*- coding:utf-8 -*-
"""
Name: Michael Beechan
School: Chongqing University of Technology
Time: 2018.10.4
Description: MINIST Digit Recognizer CNN
https://www.zhihu.com/question/52668301
"""
#卷积层1+池化层1+卷积层2+池化层2+全连接1+Dropout层+输出层
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plot
from tensorflow.examples.tutorials.mnist import input_data
import pandas as pd#Add data
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")#Get data and deal data  astype()转换数据类型
x_train = train.iloc[:, 1:].values
x_train = x_train.astype(np.float)
x_train = np.multiply(x_train, 1.0 / 255.0)#Get image width and height
image_size = x_train.shape[1]
images_width = images_height = np.ceil(np.sqrt(image_size)).astype(np.uint8)print('数据样本大小：(%g, %g)' % x_train.shape)
print('图像的维度大小：{0}'.format(image_size))
print('图像长度：{0}\n高度：{1}'.format(images_width, images_height))#Get data labels
labels_flat = train.iloc[:, 0].values.ravel()
#对于一维数组或者列表，unique函数去除其中重复的元素，并按元素由大到小返回一个新的无元素重复的元组或者列表
labels_count = np.unique(labels_flat).shape[0]#One-Hot function
def dense_to_one_hot(labels_dense, num_classes):num_labels = labels_dense.shape[0]index_offset = np.arange(num_labels) * num_classeslabels_one_hot = np.zeros((num_labels, num_classes))labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1return labels_one_hot#one-hot deal labels
labels = dense_to_one_hot(labels_flat, labels_count)
labels = labels.astype(np.uint8)print('标签({0[0]}, {0[1]})'.format(labels.shape))
print('图像标签Example：[{0}] --> {1}'.format(25, labels[25]))#Divide train data to train and validation
VALIDATION_SIZE = 2000
train_images = x_train[VALIDATION_SIZE:]
train_labels = labels[VALIDATION_SIZE:]validation_images = x_train[:VALIDATION_SIZE]
validation_labels = labels[:VALIDATION_SIZE]#set batch size and get the sum total of batch
batch_size = 100
n_batch = len(train_images) // batch_size#define Empty variable (data)x: 784 (labels)y: 10
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])#define function to deal data
def weight_variable(shape):#initial weight --- normal distribution#一个截断的产生正太分布的函数，就是说产生正太分布的值如果与均值的差值大于两倍的标准差，那就重新生成initial = tf.truncated_normal(shape, stddev=0.1)return tf.Variable(initial)def bias_variable(shape):# initial bias -- nonzeroinitial = tf.constant(0.1, shape=shape)return tf.Variable(initial)#packaging TensorFlow 2D convolution
def conv2D(x, W):return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
#packaging Tensorflow Pooling layer
def max_pool_2x2(x):return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')#Transform input data to 4D tensor, 2 and 3 is width and height, 4 is color
x_image = tf.reshape(x, [-1, 28, 28, 1])#compute 32 features 3*3 patch
w_conv1 = weight_variable([3, 3, 1, 32])
b_conv1 = bias_variable([32])#28*28 images conv step-size is 1   2*2 max pool
#After pool [28/2, 28/2] = [14, 14] the second pool [14/2, 14/2] = [7, 7]
#conv data
h_conv1 = tf.nn.relu(conv2D(x_image, w_conv1) + b_conv1)
#pool result
h_pool1 = max_pool_2x2(h_conv1)#On the previous basis, generate 64 features
w_conv2 = weight_variable([6, 6, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2D(h_pool1, w_conv2) + b_conv2)#max_pool 2*2 --> [7, 7]
h_pool2 = max_pool_2x2(h_conv2)
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])#Fully connected neural network  1024 Neural
w_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1)#Dropout
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)#1024 to 10D output
w_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, w_fc2) + b_fc2#build loss function --> cross entropy
#tf.nn.softmax_cross_entropy_with_logits
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels = y, logits=y_conv))
#optimizing para
train_step_1 = tf.train.AdadeltaOptimizer(learning_rate=0.1).minimize(loss)#compute accuracy
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_conv, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))#Set the filename parameter to save the model
global_step = tf.Variable(0, name='globle_step', trainable=False)
saver  =tf.train.Saver()#initial variable
init = tf.global_variables_initializer()#train
with tf.Session() as sess:sess.run(init)# saver.restore(sess, "model.ckpt-12")# iter 20for epoch in range(1, 20):for batch in range(n_batch):# each times get one data patch to trainbatch_x = train_images[(batch) * batch_size:(batch+1) * batch_size]batch_y = train_labels[(batch) * batch_size:(batch+1) * batch_size]# the most important step -->sess.run(train_step_1, feed_dict={x:batch_x, y:batch_y, keep_prob:0.5})# each period compute accuracyaccuracy_n = sess.run(accuracy, feed_dict={x:validation_images, y:validation_labels, keep_prob:1.0})print("The " + str(epoch+1) + "th, accuracy is " + str(accuracy_n))# save train model# global_step.assign(epoch).eval()# saver.save(sess, "model.ckpt", global_step=global_step)

接下来改进方案进一步提高准确率。。。。。使用大神的自归一化神经网络

这篇关于TensorFlow | 使用Tensorflow带你实现MNIST手写字体识别的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！


http://www.chinasem.cn/article/1034009。

相关文章

深入理解Go语言中二维切片的使用

深入理解Go语言中二维切片的使用

《深入理解Go语言中二维切片的使用》本文深入讲解了Go语言中二维切片的概念与应用,用于表示矩阵、表格等二维数据结构,文中通过示例代码介绍的非常详细,需要的朋友们下面随着小编来一起学习学习吧... 目录引言二维切片的基本概念定义创建二维切片二维切片的操作访问元素修改元素遍历二维切片二维切片的动态调整追加行动态
阅读更多...
Linux下删除乱码文件和目录的实现方式

Linux下删除乱码文件和目录的实现方式

《Linux下删除乱码文件和目录的实现方式》：本文主要介绍Linux下删除乱码文件和目录的实现方式,具有很好的参考价值,希望对大家有所帮助,如有错误或未考虑完全的地方,望不吝赐教... 目录linux下删除乱码文件和目录方法1方法2总结Linux下删除乱码文件和目录方法1使用ls -i命令找到文件或目录
阅读更多...
prometheus如何使用pushgateway监控网路丢包

prometheus如何使用pushgateway监控网路丢包

《prometheus如何使用pushgateway监控网路丢包》：本文主要介绍prometheus如何使用pushgateway监控网路丢包问题,具有很好的参考价值,希望对大家有所帮助,如有错误... 目录监控网路丢包脚本数据图表总结监控网路丢包脚本[root@gtcq-gt-monitor-prome
阅读更多...
SpringBoot+EasyExcel实现自定义复杂样式导入导出

SpringBoot+EasyExcel实现自定义复杂样式导入导出

《SpringBoot+EasyExcel实现自定义复杂样式导入导出》这篇文章主要为大家详细介绍了SpringBoot如何结果EasyExcel实现自定义复杂样式导入导出功能,文中的示例代码讲解详细,... 目录安装处理自定义导出复杂场景1、列不固定，动态列2、动态下拉3、自定义锁定行/列，添加密码4、合并
阅读更多...
mybatis执行insert返回id实现详解

mybatis执行insert返回id实现详解

《mybatis执行insert返回id实现详解》MyBatis插入操作默认返回受影响行数,需通过useGeneratedKeys+keyProperty或selectKey获取主键ID,确保主键为自... 目录 两种方式获取自增 ID：1. ​​useGeneratedKeys+keyProperty（推
阅读更多...
Spring Boot集成Druid实现数据源管理与监控的详细步骤

Spring Boot集成Druid实现数据源管理与监控的详细步骤

《SpringBoot集成Druid实现数据源管理与监控的详细步骤》本文介绍如何在SpringBoot项目中集成Druid数据库连接池,包括环境搭建、Maven依赖配置、SpringBoot配置文件... 目录1. 引言1.1 环境准备1.2 Druid介绍2. 配置Druid连接池3. 查看Druid监控
阅读更多...
Python通用唯一标识符模块uuid使用案例详解

Python通用唯一标识符模块uuid使用案例详解

《Python通用唯一标识符模块uuid使用案例详解》Pythonuuid模块用于生成128位全局唯一标识符,支持UUID1-5版本,适用于分布式系统、数据库主键等场景,需注意隐私、碰撞概率及存储优... 目录简介核心功能1. UUID版本2. UUID属性3. 命名空间使用场景1. 生成唯一标识符2. 数
阅读更多...
Linux在线解压jar包的实现方式

Linux在线解压jar包的实现方式

《Linux在线解压jar包的实现方式》：本文主要介绍Linux在线解压jar包的实现方式,具有很好的参考价值,希望对大家有所帮助,如有错误或未考虑完全的地方,望不吝赐教... 目录linux在线解压jar包解压 jar包的步骤总结Linux在线解压jar包在 Centos 中解压 jar 包可以使用 u
阅读更多...
SpringBoot中如何使用Assert进行断言校验

SpringBoot中如何使用Assert进行断言校验

《SpringBoot中如何使用Assert进行断言校验》Java提供了内置的assert机制,而Spring框架也提供了更强大的Assert工具类来帮助开发者进行参数校验和状态检查,下... 目录前言一、Java 原生assert简介1.1 使用方式1.2 示例代码1.3 优缺点分析二、Spring Fr
阅读更多...
Android kotlin中 Channel 和 Flow 的区别和选择使用场景分析

Android kotlin中 Channel 和 Flow 的区别和选择使用场景分析

《Androidkotlin中Channel和Flow的区别和选择使用场景分析》Kotlin协程中,Flow是冷数据流,按需触发,适合响应式数据处理；Channel是热数据流,持续发送,支持... 目录一、基本概念界定FlowChannel二、核心特性对比数据生产触发条件生产与消费的关系背压处理机制生命周期
阅读更多...

Copyright China编程 23002807@qq.com

沪ICP备2023033072号-2