准确率只有70%，cpu版本的TF居然跑了两天才跑完，其他方法将继续尝试。

生成数据目录：

import numpy as np

import os

train_label = {}

for i in range(10):

    search_path = './data/train/{}'.format(i)

    file_list = os.listdir(search_path)

    for file in file_list:

        train_label[os.path.join(search_path, file)] = i

np.save('label.npy', train_label)

test_label = {}

for i in range(10):

    search_path = './data/test/{}'.format(i)

    file_list = os.listdir(search_path)

    for file in file_list:

        test_label[os.path.join(search_path, file)] = i

np.save('test-label.npy', test_label)

训练：

import tensorflow as tf

import numpy as np

import random

import cv2

# 将传入的label转换成one hot的形式。

def getOneHotLabel(label, depth):

    m = np.zeros([len(label), depth])

    for i in range(len(label)):

        m[i][label[i]] = 1

    return m

# 建立神经网络。

def alexnet(image, keepprob=0.5):

    # 定义卷积层1，卷积核大小，偏置量等各项参数参考下面的程序代码，下同。

    with tf.name_scope("conv1") as scope:

        kernel = tf.Variable(tf.truncated_normal([11, 11, 3, 64], dtype=tf.float32, stddev=1e-1, name="weights"))

        conv = tf.nn.conv2d(image, kernel, [1, 4, 4, 1], padding="SAME")

        biases = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[64]), trainable=True, name="biases")

        bias = tf.nn.bias_add(conv, biases)

        conv1 = tf.nn.relu(bias, name=scope)

        pass

    # LRN层

    lrn1 = tf.nn.lrn(conv1, 4, bias=1.0, alpha=0.001/9, beta=0.75, name="lrn1")

    # 最大池化层

    pool1 = tf.nn.max_pool(lrn1, ksize=[1,3,3,1], strides=[1,2,2,1],padding="VALID", name="pool1")

    # 定义卷积层2

    with tf.name_scope("conv2") as scope:

        kernel = tf.Variable(tf.truncated_normal([5,5,64,192], dtype=tf.float32, stddev=1e-1, name="weights"))

        conv = tf.nn.conv2d(pool1, kernel, [1, 1, 1, 1], padding="SAME")

        biases = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[192]), trainable=True, name="biases")

        bias = tf.nn.bias_add(conv, biases)

        conv2 = tf.nn.relu(bias, name=scope)

        pass

    # LRN层

    lrn2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9, beta=0.75, name="lrn2")

    # 最大池化层

    pool2 = tf.nn.max_pool(lrn2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding="VALID", name="pool2")

    # 定义卷积层3

    with tf.name_scope("conv3") as scope:

        kernel = tf.Variable(tf.truncated_normal([3,3,192,384], dtype=tf.float32, stddev=1e-1, name="weights"))

        conv = tf.nn.conv2d(pool2, kernel, [1, 1, 1, 1], padding="SAME")

        biases = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[384]), trainable=True, name="biases")

        bias = tf.nn.bias_add(conv, biases)

        conv3 = tf.nn.relu(bias, name=scope)

        pass

    # 定义卷积层4

    with tf.name_scope("conv4") as scope:

        kernel = tf.Variable(tf.truncated_normal([3,3,384,256], dtype=tf.float32, stddev=1e-1, name="weights"))

        conv = tf.nn.conv2d(conv3, kernel, [1, 1, 1, 1], padding="SAME")

        biases = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[256]), trainable=True, name="biases")

        bias = tf.nn.bias_add(conv, biases)

        conv4 = tf.nn.relu(bias, name=scope)

        pass

    # 定义卷积层5

    with tf.name_scope("conv5") as scope:

        kernel = tf.Variable(tf.truncated_normal([3,3,256,256], dtype=tf.float32, stddev=1e-1, name="weights"))

        conv = tf.nn.conv2d(conv4, kernel, [1, 1, 1, 1], padding="SAME")

        biases = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[256]), trainable=True, name="biases")

        bias = tf.nn.bias_add(conv, biases)

        conv5 = tf.nn.relu(bias, name=scope)

        pass

    # 最大池化层

    pool5 = tf.nn.max_pool(conv5, ksize=[1,3,3,1], strides=[1,2,2,1], padding="VALID", name="pool5")

    # 全连接层

    flatten = tf.reshape(pool5, [-1, 6*6*256])

    weight1 = tf.Variable(tf.truncated_normal([6*6*256, 4096], mean=0, stddev=0.01))

    fc1 = tf.nn.sigmoid(tf.matmul(flatten, weight1))

    dropout1 = tf.nn.dropout(fc1, keepprob)

    weight2 = tf.Variable(tf.truncated_normal([4096, 4096], mean=0, stddev=0.01))

    fc2 = tf.nn.sigmoid(tf.matmul(dropout1, weight2))

    dropout2 = tf.nn.dropout(fc2, keepprob)

    weight3 = tf.Variable(tf.truncated_normal([4096, 10], mean=0, stddev=0.01))

    fc3 = tf.nn.sigmoid(tf.matmul(dropout2, weight3))

    return fc3

def alexnet_main():

    # 加载使用的训练集文件名和标签。

    files = np.load("label.npy",  allow_pickle=True , encoding='bytes')[()]

    # 提取文件名。

    keys = [i for i in files]

    print(len(keys))

    myinput = tf.placeholder(dtype=tf.float32, shape=[None, 224, 224, 3], name='input')

    mylabel = tf.placeholder(dtype=tf.float32, shape=[None, 10], name='label')

    # 建立网络，keepprob为0.6。

    myoutput = alexnet(myinput, 0.6)

    # 定义训练的loss函数。

    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=myoutput, labels=mylabel))

    # 定义优化器，学习率设置为0.09，学习率可以设置为其他的数值。

    optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.09).minimize(loss)

    # 定义准确率

    valaccuracy = tf.reduce_mean(

        tf.cast(

            tf.equal(

                tf.argmax(myoutput, 1),

                tf.argmax(mylabel, 1)),

            tf.float32))

    # tensorflow的saver，可以用于保存模型。

    saver = tf.train.Saver()

    init = tf.global_variables_initializer()

    with tf.Session() as sess:

        sess.run(init)

        # 40个epoch

        for loop in range(40):

            # 生成并打乱训练集的顺序。

            indices = np.arange(50000)

            random.shuffle(indices)

            # batch size此处定义为200。

            # 训练集一共50000张图片，前40000张用于训练，后10000张用于验证集。

            for i in range(0, 0+40000, 200):

                photo = []

                label = []

                for j in range(0, 200):

                    # print(keys[indices[i + j]])

                    photo.append(cv2.resize(cv2.imread(keys[indices[i + j]]), (224, 224))/225)

                    label.append(files[keys[indices[i + j]]])

                m = getOneHotLabel(label, depth=10)

                a, b = sess.run([optimizer, loss], feed_dict={myinput: photo, mylabel: m})

                print("\r%lf"%b, end='')

            acc = 0

            # 每次取验证集的200张图片进行验证，返回这200张图片的正确率。

            for i in range(40000, 40000+10000, 200):

                photo = []

                label = []

                for j in range(i, i + 200):

                    photo.append(cv2.resize(cv2.imread(keys[indices[j]]), (224, 224))/225)

                    label.append(files[keys[indices[j]]])

                m = getOneHotLabel(label, depth=10)

                acc += sess.run(valaccuracy, feed_dict={myinput: photo, mylabel: m})

            # 输出，一共有50次验证集数据相加，所以需要除以50。

            print("Epoch ", loop, ': validation rate: ', acc/50)

        # 保存模型。

        saver.save(sess, "model/model.ckpt")

if __name__ == '__main__':

    alexnet_main()

测试：

import tensorflow as tf

import numpy as np

import random

import cv2

def getOneHotLabel(label, depth):

    m = np.zeros([len(label), depth])

    for i in range(len(label)):

        m[i][label[i]] = 1

    return m

# 建立神经网络

def alexnet(image, keepprob=0.5):

    # 定义卷积层1，卷积核大小，偏置量等各项参数参考下面的程序代码，下同

    with tf.name_scope("conv1") as scope:

        kernel = tf.Variable(tf.truncated_normal([11, 11, 3, 64], dtype=tf.float32, stddev=1e-1, name="weights"))

        conv = tf.nn.conv2d(image, kernel, [1, 4, 4, 1], padding="SAME")

        biases = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[64]), trainable=True, name="biases")

        bias = tf.nn.bias_add(conv, biases)

        conv1 = tf.nn.relu(bias, name=scope)

        pass

    # LRN层

    lrn1 = tf.nn.lrn(conv1, 4, bias=1.0, alpha=0.001/9, beta=0.75, name="lrn1")

    # 最大池化层

    pool1 = tf.nn.max_pool(lrn1, ksize=[1,3,3,1], strides=[1,2,2,1],padding="VALID", name="pool1")

    # 定义卷积层2

    with tf.name_scope("conv2") as scope:

        kernel = tf.Variable(tf.truncated_normal([5,5,64,192], dtype=tf.float32, stddev=1e-1, name="weights"))

        conv = tf.nn.conv2d(pool1, kernel, [1, 1, 1, 1], padding="SAME")

        biases = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[192]), trainable=True, name="biases")

        bias = tf.nn.bias_add(conv, biases)

        conv2 = tf.nn.relu(bias, name=scope)

        pass

    # LRN层

    lrn2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9, beta=0.75, name="lrn2")

    # 最大池化层

    pool2 = tf.nn.max_pool(lrn2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding="VALID", name="pool2")

    # 定义卷积层3

    with tf.name_scope("conv3") as scope:

        kernel = tf.Variable(tf.truncated_normal([3,3,192,384], dtype=tf.float32, stddev=1e-1, name="weights"))

        conv = tf.nn.conv2d(pool2, kernel, [1, 1, 1, 1], padding="SAME")

        biases = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[384]), trainable=True, name="biases")

        bias = tf.nn.bias_add(conv, biases)

        conv3 = tf.nn.relu(bias, name=scope)

        pass

    # 定义卷积层4

    with tf.name_scope("conv4") as scope:

        kernel = tf.Variable(tf.truncated_normal([3,3,384,256], dtype=tf.float32, stddev=1e-1, name="weights"))

        conv = tf.nn.conv2d(conv3, kernel, [1, 1, 1, 1], padding="SAME")

        biases = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[256]), trainable=True, name="biases")

        bias = tf.nn.bias_add(conv, biases)

        conv4 = tf.nn.relu(bias, name=scope)

        pass

    # 定义卷积层5

    with tf.name_scope("conv5") as scope:

        kernel = tf.Variable(tf.truncated_normal([3,3,256,256], dtype=tf.float32, stddev=1e-1, name="weights"))

        conv = tf.nn.conv2d(conv4, kernel, [1, 1, 1, 1], padding="SAME")

        biases = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[256]), trainable=True, name="biases")

        bias = tf.nn.bias_add(conv, biases)

        conv5 = tf.nn.relu(bias, name=scope)

        pass

    # 最大池化层

    pool5 = tf.nn.max_pool(conv5, ksize=[1,3,3,1], strides=[1,2,2,1], padding="VALID", name="pool5")

    # 全连接层

    flatten = tf.reshape(pool5, [-1, 6*6*256])

    weight1 = tf.Variable(tf.truncated_normal([6*6*256, 4096], mean=0, stddev=0.01))

    fc1 = tf.nn.sigmoid(tf.matmul(flatten, weight1))

    dropout1 = tf.nn.dropout(fc1, keepprob)

    weight2 = tf.Variable(tf.truncated_normal([4096, 4096], mean=0, stddev=0.01))

    fc2 = tf.nn.sigmoid(tf.matmul(dropout1, weight2))

    dropout2 = tf.nn.dropout(fc2, keepprob)

    weight3 = tf.Variable(tf.truncated_normal([4096, 10], mean=0, stddev=0.01))

    fc3 = tf.nn.sigmoid(tf.matmul(dropout2, weight3))

    return fc3

def alexnet_main():

    # 加载测试集的文件名和标签。

    files = np.load("test-label.npy", encoding='bytes')[()]

    keys = [i for i in files]

    print(len(keys))

    myinput = tf.placeholder(dtype=tf.float32, shape=[None, 224, 224, 3], name='input')

    mylabel = tf.placeholder(dtype=tf.float32, shape=[None, 10], name='label')

    myoutput = alexnet(myinput, 0.6)

    prediction = tf.argmax(myoutput, 1)

    truth = tf.argmax(mylabel, 1)

    valaccuracy = tf.reduce_mean(

        tf.cast(

            tf.equal(

                prediction,

                truth),

            tf.float32))

    saver = tf.train.Saver()

    with tf.Session() as sess:

        # 加载训练好的模型，路径根据自己的实际情况调整

        saver.restore(sess, r"model/model.ckpt")

        cnt = 0

        for i in range(10000):

            photo = []

            label = []

            photo.append(cv2.resize(cv2.imread(keys[i]), (224, 224))/225)

            label.append(files[keys[i]])

            m = getOneHotLabel(label, depth=10)

            a, b= sess.run([prediction, truth], feed_dict={myinput: photo, mylabel: m})

            print(a, ' ', b)

            if a[0] == b[0]:

                cnt += 1

        print("Epoch ", 1, ': prediction rate: ', cnt / 10000)

if __name__ == '__main__':

    alexnet_main()

TensorFlow笔记六：基于cifar10数据库的AlexNet识别的更多相关文章

  1. EF Core使用笔记（基于MySql数据库）

    一.什么是EF Entity Framework 是适用于.NET 的对象关系映射程序 (O/RM). 二.比较 EF Core 和 EF6 1.Entity Framework 6 Entity F ...

  2. java之jvm学习笔记六-十二(实践写自己的安全管理器)(jar包的代码认证和签名) (实践对jar包的代码签名) (策略文件)(策略和保护域) (访问控制器) (访问控制器的栈校验机制) (jvm基本结构)

    java之jvm学习笔记六(实践写自己的安全管理器) 安全管理器SecurityManager里设计的内容实在是非常的庞大,它的核心方法就是checkPerssiom这个方法里又调用 AccessCo ...

  3. tensorflow笔记:使用tf来实现word2vec

    (一) tensorflow笔记:流程,概念和简单代码注释 (二) tensorflow笔记:多层CNN代码分析 (三) tensorflow笔记:多层LSTM代码分析 (四) tensorflow笔 ...

  4. tensorflow笔记（一）之基础知识

    tensorflow笔记(一)之基础知识 版权声明:本文为博主原创文章,转载请指明转载地址 http://www.cnblogs.com/fydeblog/p/7399701.html 前言 这篇no ...

  5. Python学习笔记六

    Python课堂笔记六 常用模块已经可以在单位实际项目中使用,可以实现运维自动化.无需手工备份文件,数据库,拷贝,压缩. 常用模块 time模块 time.time time.localtime ti ...

  6. tensorflow笔记：多层LSTM代码分析

    tensorflow笔记:多层LSTM代码分析 标签(空格分隔): tensorflow笔记 tensorflow笔记系列: (一) tensorflow笔记:流程,概念和简单代码注释 (二) ten ...

  7. TensorFlow笔记-08-过拟合,正则化,matplotlib 区分红蓝点

    TensorFlow笔记-08-过拟合,正则化,matplotlib 区分红蓝点 首先提醒一下,第7讲的最后滑动平均的代码已经更新了,代码要比理论重要 今天是过拟合,和正则化,本篇后面可能或更有兴趣, ...

  8. TensorFlow笔记-06-神经网络优化-损失函数,自定义损失函数,交叉熵

    TensorFlow笔记-06-神经网络优化-损失函数,自定义损失函数,交叉熵 神经元模型:用数学公式比表示为:f(Σi xi*wi + b), f为激活函数 神经网络 是以神经元为基本单位构成的 激 ...

  9. TensorFlow笔记-05-反向传播,搭建神经网络的八股

    TensorFlow笔记-05-反向传播,搭建神经网络的八股 反向传播 反向传播: 训练模型参数,在所有参数上用梯度下降,使用神经网络模型在训练数据上的损失函数最小 损失函数:(loss) 计算得到的 ...

随机推荐

  1. dijkstra 堆优化

    #include <iostream> #include <vector> #include <cstring> #include <queue> us ...

  2. hnust CZJ-Superman

    问题 B: CZJ-Superman 时间限制: 1 Sec  内存限制: 128 MB提交: 636  解决: 87[提交][状态][讨论版] 题目描述 “那是只鸟?那是飞机?那是——超人!” 程序 ...

  3. [转载]用等高线图（Contour maps）可视化多变量函数

    https://blog.csdn.net/xlinsist/article/details/50920479 Overview 由于我们用手来画三维图像很困难,我们可以用等高线图来描述图像会更加简单 ...

  4. JavaWeb笔记（二）Servlet

    Tomcat目录简介 bin--可执行文件 conf--配置文件 lib--依赖jar包 logs--日志文件 temp--临时文件 webapps--默认项目部署路径 work--存放运行时的数据 ...

  5. CI在nginx环境下去掉url中的index.php

    在nginx环境下CI框架默认URL规则访问不了,出现500错误,如: http://blog.php230.com/index.php/keywords 今天在服务器配置CI框架环境时,去除URL中 ...

  6. Android jni 编程入门

    本文将介绍如何使用eclipse和ndk-build来编写一个基于Android4.4版本的包含有.so动态库的安卓程序. 前提是已经安装和配置好了诸如SDK,NDK等编译环境.下面开始编程! 1 程 ...

  7. Java EE 学习（5）：IDEA + maven + spring 搭建 web（1）

    参考:http://www.cnblogs.com/lonelyxmas/p/5397422.html http://www.ctolib.com/docs-IntelliJ-IDEA-c--1590 ...

  8. 【16】vuex2.0 之 getter

    有的组件中获取到 store 中的state,  需要对进行加工才能使用,computed 属性中就需要写操作函数,如果有多个组件中都需要进行这个操作,那么在各个组件中都写相同的函数,那就非常麻烦,这 ...

  9. Cannot map 'XXXController.Create' bean method

    [转 :http://www.fanfanyu.cn/news/staticpagefile/2351.html] 最近在开发项目的过程中SpringMVC抛了个"Ambiguous map ...

  10. 利用GridView控件导出其他文件（导出Excel，导出Word文件）

    原文发布时间为:2008-10-16 -- 来源于本人的百度文章 [由搬家工具导入] // 注意，在Visual Studio2005平台下，如果使用GridView导出文件，      //就必须重 ...