手写数字识别全部代码--全连接神经网络方法

'''
#2018-06-25 272015 June Monday the 26 week, the 176 day SZ
手写字体识别程序文件1：
这个程序使用了全连接神经网络也就是DNN。
定义了前向传播的过程以及神经网络中的参数,无论训练还是测试，都可以直接调用inference这个函数
问题代码：
#regularizer正则化矩阵，变量属性：维度，shape；tf.truncated_normal_initializer 从截断的正态分布中输出随机值。seed：一个Python整数。用于创建随机种子。查看 tf.set_random_seed 行为。  tf.nn.relu() 激活函数实现去线性化
神经网络结果加上激活函数和偏置项：f(Wx +b); f(x)是激活函数，b是偏置项
每个神经元的输出经过非线性函数，整个模型就不是非线性了。这个非线性函数就是激活函数。
三个常见激活函数：ReLU激活函数，Sigmoid激活函数，tanh函数；
'''import tensorflow as tf #定义输入，输出，隐藏层1的节点个数
INPUT_NODE = 784 #28*28
OUTPUT_NODE = 10 #输出10个结点，十种分类结果，对应0-9数字
LAYER1_NODE = 500 #隐藏层有500个结点def get_weight_variable(shape, regularizer): #regularizer正则化矩阵，变量属性：维度，shape；truncated缩短了的；被删节的；切去顶端的weights = tf.get_variable('weights',shape, initializer = tf.truncated_normal_initializer(stddev=0.1))#张量加入集合lossesif regularizer != None:tf.add_to_collection('losses', regularizer(weights))return weights#定义前向传播过程
def inference(input_tensor, regularizer):#声明第一层神经网络的过程并完成前向传播的过程with tf.variable_scope('layer1'):weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer) #[INPUT_NODE, LAYER1_NODE]之间的权重biases = tf.get_variable('biases', [LAYER1_NODE], initializer = tf.constant_initializer(0.0))layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)#声明第2层神经网络的过程并完成前向传播的过程with tf.variable_scope('layer2'):weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer) #[LAYER1_NODE, OUTPUT_NODE]之间的权重biases = tf.get_variable('biases', [OUTPUT_NODE], initializer = tf.constant_initializer(0.0))layer2 = tf.matmul(layer1, weights) + biases#返回前向传播结果return layer2###########################################以下是训练部分###########################################import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import osBATCH_SIZE = 100  #每批次取100个；一个批次中训练个数。
LEARNING_RATE_BASE = 0.8 #学习率初始值
LEARNING_RATE_DECAY = 0.99 #学习率衰减率
REGULARIZATION_RATE = 0.0001 #正则化系数
TRAINING_STEPS = 30000 #训练轮数
MOVING_AVERAGE_DECAY = 0.99 #滑动平均衰减率，控制模型更新的速度，让模型在测试数据上更健壮
MODEL_SAVE_PATH = 'D:\\ST\\Python_work\\program\\手写识别'
MODEL_NAME = "mnist_model"def train(mnist):# 定义输入输出placeholder。placeholder定义了一个位置，程序运行时候给这个位置提供数据。这个机制提供输入数据x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE) #L2范数正则化y = mnist_inference.inference(x, regularizer) #预测值global_step = tf.Variable(0, trainable=False) #定义存储训练轮数的变量# 定义损失函数、学习率、滑动平均操作以及训练过程。variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)variables_averages_op = variable_averages.apply(tf.trainable_variables())cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))cross_entropy_mean = tf.reduce_mean(cross_entropy)loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses')) #总损失=交叉熵损失和正则化损失learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, #基础学习率global_step,       #当前迭代轮数mnist.train.num_examples / BATCH_SIZE, #过完所有训练数据需要的迭代次数LEARNING_RATE_DECAY,                  #学习率衰减速度staircase=True)train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)#每次循环需要通过反向传播来更新参数，又要更新参数的每一个滑动平均值with tf.control_dependencies([train_step, variables_averages_op]):train_op = tf.no_op(name='train')# 初始化TensorFlow持久化类。saver = tf.train.Saver()#初始化会话，开始训练过程with tf.Session() as sess:tf.global_variables_initializer().run()for i in range(TRAINING_STEPS):xs, ys = mnist.train.next_batch(BATCH_SIZE)_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})if i % 1000 == 0: #每1000轮输出一次损失，保存模型，实现持久化print("After %d training step(s), loss on training batch is %g." % (step, loss_value))saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step) #def main(argv=None):mnist = input_data.read_data_sets('D:\\ST\\Python_work\\program\\手写识别', one_hot=True)train(mnist)if __name__ == '__main__':main()'''Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes.
Extracting D:\ST\Python_work\program\手写识别\train-images-idx3-ubyte.gz
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Extracting D:\ST\Python_work\program\手写识别\train-labels-idx1-ubyte.gz
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.
Extracting D:\ST\Python_work\program\手写识别\t10k-images-idx3-ubyte.gz
Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes.
Extracting D:\ST\Python_work\program\手写识别\t10k-labels-idx1-ubyte.gz
2018-06-25 19:14:55.952000: I C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\35\tensorflow\core\platform\cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
After 1 training step(s), loss on training batch is 2.96337.
After 1001 training step(s), loss on training batch is 0.21122.
After 2001 training step(s), loss on training batch is 0.195296.
After 3001 training step(s), loss on training batch is 0.147966.
After 4001 training step(s), loss on training batch is 0.121113.
After 5001 training step(s), loss on training batch is 0.104925.
After 6001 training step(s), loss on training batch is 0.0969063.
After 7001 training step(s), loss on training batch is 0.0967676.
After 8001 training step(s), loss on training batch is 0.0805094.
After 9001 training step(s), loss on training batch is 0.0758026.
After 10001 training step(s), loss on training batch is 0.0662473.
After 11001 training step(s), loss on training batch is 0.0667674.
After 12001 training step(s), loss on training batch is 0.0615224.
After 13001 training step(s), loss on training batch is 0.0548805.
After 14001 training step(s), loss on training batch is 0.0576472.
After 15001 training step(s), loss on training batch is 0.0558432.
After 16001 training step(s), loss on training batch is 0.050817.
After 17001 training step(s), loss on training batch is 0.04974.
After 18001 training step(s), loss on training batch is 0.0424435.
After 19001 training step(s), loss on training batch is 0.0423194.
After 20001 training step(s), loss on training batch is 0.0413847.
After 21001 training step(s), loss on training batch is 0.0433296.
After 22001 training step(s), loss on training batch is 0.0370582.
After 23001 training step(s), loss on training batch is 0.0422068.
After 24001 training step(s), loss on training batch is 0.0377206.
After 25001 training step(s), loss on training batch is 0.0377879.
After 26001 training step(s), loss on training batch is 0.0397268.
After 27001 training step(s), loss on training batch is 0.035891.
After 28001 training step(s), loss on training batch is 0.0405907.
After 29001 training step(s), loss on training batch is 0.0337722.
[Finished in 479.9s]
''''''
'''
###########################################我的问题代码训练部分###########################################我的问题代码2
源码地址：
https://github.com/caicloud/tensorflow-tutorial/tree/master/Deep_Learning_with_TensorFlow#2018-06-25 272015 June Monday the 26 week, the 176 day SZ
手写字体识别程序文件1：
定义了神经网络的训练过程'''
import os
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data#加载mnist_inference.py中定义的常量和前向传播的函数
import mnist_inference#配置神经网络的参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARAZTION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
#模型保存路径和文件名
MODEL_SAVE_PATH = 'D:\\ST\\Python_work\\program\\手写识别'
MODEL_NAME = 'model.ckpt'def train(mnist):#定义输入输出placeholder.x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE],name = 'x-input')y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name = 'y-input')regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)#直接使用mnist_inference.py中定义的前向传播过程y = mnist_inference.inference(x, regularizer)global_step = tf.Variable(0, trainable = False)#定义损失函数，学习率，滑动平均操作以及训练过程variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)variables_averages_op = variable_averages.apply(tf.trainable_variables())cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(y, tf.argmax(y_, 1))cross_entropy_mean = tf.reduce_mean(cross_entropy)loss = cross_entropy_mean +tf.add_n(tf.get_collection('losses'))learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY)train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step = global_step)with tf.control_dependencies([train_step, variables_averages_op]):train_op = tf.no_op(name='train')#初始化tf持久化类saver = tf.train.Saver()with tf.Session() as sess:tf.initialize_all_variables().run()tf.global_variables_initializer().run()#在训练过程中不再测试模型在验证数据上的表现，验证和测试的过程有一个独立程序完成for i in range(TRAINING_STEPS):xs, ys = mnist.train.next_batch(BATCH_SIZE)_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict = {x:xs, y_:ys})#每1000轮保存一次模型if i % 1000 ==0:#输出当前损失函数print('After %d training step(s) , loss on training batch is %g'%(step, loss_value))#保存模型，文件尾部加上训练轮数saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step = global_step)def main(argv = None):mnist = input_data.read_data_sets('D:\\ST\\Python_work\\program\\手写识别', one_hot = True)train(mnist)if __name__ == '__main__':tf.app.run()'''###########################################以下是预测部分############################################老师代码3
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train# 加载的时间间隔。每十秒加载一次最新模型，并在测试数据上测试最新模型的正确率
EVAL_INTERVAL_SECS = 50def evaluate(mnist):with tf.Graph().as_default() as g:x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')#准备验证数据集validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}#预测值，用封装好的函数来计算前向传播的结果y = mnist_inference.inference(x, None)#正确预测，使用前向传播结果计算正确率。tf.argmax(y_, 1)得到输入样例的预测类别correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))#变量重命名的方式加载模型，这样不用调用求滑动平均的函数来获取平均值了。variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)variables_to_restore = variable_averages.variables_to_restore()saver = tf.train.Saver(variables_to_restore)while True:with tf.Session() as sess:#MODEL_SAVE_PATH = 'D:\\ST\\Python_work\\program\\手写识别'#checkpoint文件自动找到目录中最新模型的文件名ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)#print(ckpt)  #None找不到该文件，我明明看到有这个文件呢。if ckpt and ckpt.model_checkpoint_path:#加载模型saver.restore(sess, ckpt.model_checkpoint_path)#通过文件名得到模型保存时迭代的轮数global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]accuracy_score = sess.run(accuracy, feed_dict=validate_feed)print("After %s training step(s), validation accuracy = %g" % (global_step, accuracy_score))else:print('No checkpoint file found')returntime.sleep(EVAL_INTERVAL_SECS)def main(argv=None):mnist = input_data.read_data_sets('D:\\ST\\Python_work\\program\\手写识别', one_hot=True)evaluate(mnist)if __name__ == '__main__':main()'''
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Extracting D:\ST\Python_work\program\手写识别\train-labels-idx1-ubyte.gz
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.
Extracting D:\ST\Python_work\program\手写识别\t10k-images-idx3-ubyte.gz
Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes.
Extracting D:\ST\Python_work\program\手写识别\t10k-labels-idx1-ubyte.gz
2018-06-25 19:35:27.932000: I C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\35\tensorflow\core\platform\cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
No checkpoint file found
[Finished in 19.6s]
''''''
###########################################我的问题代码预测部分############################################自己代码
'''
#2018-06-25 272015 June Monday the 26 week, the 176 day SZ
手写字体识别程序文件3：
定义了前向传播的过程以及神经网络中的参数
'''
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data#加载mnist_inference.py 和mnist_train.py中定义的常量和函数
import mnist_inference
import mnist_train#10秒加载一次最新的模型，并且在测试集上测试最新模型的正确率
EVAL_INTERVAL_SECS = 10def evaluate(mnist):with tf.Graph().as_default() as g:#定义输入输出格式x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name = 'x- input')y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name = 'y- input')validate_feed = {x:mnist.validation.images, y_:mnist.validation.labels}#直接调用其他文档的函数进行计算前向传播结果y = mnist_inference.inference(x, None)#使用前向结果计算正确率correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))#通过变量重命名的方式加载模型，这样在前向传播过程中就不要调用求滑动平均的函数来获取平均值了。这样可以完全共用#mnist_inference.py中定义的前向传播过程variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)variables_to_restore = variable_averages.variables_to_restore()saver = tf.train.Saver(variables_to_restore)#每隔EVAL_INTERVAL_SECS秒调用一次计算正确率的过程来检测训练过程中正确率的变化while True:with tf.Session() as sess:#tf.train.get_checkpoint_state()会通过checkpoint文件自动找到目录中最新模型的文件名字ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)if ckpt and ckpt.model_checkpoint_path:#加载模型saver.restore(sess, ckpt.model_checkpoint_path)#通过文件名字得到模型保存时候迭代的轮数global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]accuracy_score = sess.run(accuracy, feed_dict = validation_feed)print('After %s training steps, validation accuracy = %g'%(global_step, accuracy_score))else:print('no checkpoint file found')return time.sleep(EVAL_INTERVAL_SECS)def main(argv=None):mnist = input_data.read_data_sets('D:\\ST\\Python_work\\program\\手写识别', one_hot = True)evaluate(mnist)if __name__ == '__main__':tf.app.run()
'''

手写数字识别全部代码--全连接神经网络方法相关推荐

1、基于Keras、Mnist手写数字识别数据集构建全连接（FC）神经网络训练模型
文章目录前言一.MNIST数据集是什么? 二.构建神经网络训练模型 1.导入库 2.载入数据 3.数据处理 4.创建模型 5.编译模型 6.训练模型 7.评估模型三.总代码前言提示: 1.本 ...
飞桨day-01手写数字识别实践（使用卷积神经网络）
day-01高层API手写数字识别实践(使用卷积神经网络) AI Studio项目地址:https://aistudio.baidu.com/aistudio/projectdetail/150477 ...
基于CNN的MINIST手写数字识别项目代码以及原理详解
文章目录项目简介项目下载地址项目开发软件环境项目开发硬件环境前言一.数据加载的作用二.Pytorch进行数据加载所需工具 2.1 Dataset 2.2 Dataloader 2.3 T ...
【图像识别】基于卷积神经网络CNN手写数字识别matlab代码
1 简介针对传统手写数字的随机性,无规律性等问题,为了提高手写数字识别的检测准确性,本文在研究手写数字区域特点的基础上,提出了一种新的手写数字识别检测方法.首先,对采集的手写数字图像进行预处理,由于 ...
手写数字识别项目代码——卷积神经网络LeNet-5模型
''' #2018-06-25 272015 June Monday the 26 week, the 176 day SZ 手写字体识别程序文件1: 这个程序使用了卷积神经网络LeNet - 5模型 ...
python手写英文识别_pytorch三层全连接层实现手写字母识别方式
先用最简单的三层全连接神经网络,然后添加激活层查看实验结果,最后加上批标准化验证是否有效首先根据已有的模板定义网络结构SimpleNet,命名为net.py import torch from to ...
使用Caffe进行手写数字识别执行流程解析
之前在 http://blog.csdn.net/fengbingchun/article/details/50987185 中仿照Caffe中的examples实现对手写数字进行识别,这里详细介绍下 ...
Java软件研发工程师转行之深度学习(Deep Learning)进阶：手写数字识别+人脸识别+图像中物体分类+视频分类+图像与文字特征+猫狗分类
本文适合于对机器学习和数据挖掘有所了解,想深入研究深度学习的读者 1.对概率基本概率有所了解 2.具有微积分和线性代数的基本知识 3.有一定的编程基础(Python) Java软件研发工程师转行之深度 ...
机器学习笔记——从手写数字识别开始
文章目录前言关于这篇博客(预计八月下旬全部完成) 关于项目实现监督学习 ANN全连接神经网络的实现 1.总述 2.初始化 3.传播及损失 4.反向传播决策树以及随机森林的实现 1.总述 2.单 ...

手写数字识别全部代码--全连接神经网络方法

手写数字识别全部代码--全连接神经网络方法相关推荐

最新文章

热门文章