import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data

import time

# 声明输入图片数据，类别

x = tf.placeholder('float', [None, 784])

y_ = tf.placeholder('float', [None, 10])

# 输入图片数据转化

x_image = tf.reshape(x, [-1, 28, 28, 1])

#第一层卷积层，初始化卷积核参数、偏置值，该卷积层5*5大小，一个通道，共有6个不同卷积核

filter1 = tf.Variable(tf.truncated_normal([5, 5, 1, 6]))

bias1 = tf.Variable(tf.truncated_normal([6]))

conv1 = tf.nn.conv2d(x_image, filter1, strides=[1, 1, 1, 1], padding='SAME')

h_conv1 = tf.nn.relu(conv1 + bias1)

maxPool2 = tf.nn.max_pool(h_conv1, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')

filter2 = tf.Variable(tf.truncated_normal([5, 5, 6, 16]))

bias2 = tf.Variable(tf.truncated_normal([16]))

conv2 = tf.nn.conv2d(maxPool2, filter2, strides=[1, 1, 1, 1], padding='SAME')

h_conv2 = tf.nn.relu(conv2 + bias2)

maxPool3 = tf.nn.max_pool(h_conv2, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')

filter3 = tf.Variable(tf.truncated_normal([5, 5, 16, 120]))

bias3 = tf.Variable(tf.truncated_normal([120]))

conv3 = tf.nn.conv2d(maxPool3, filter3, strides=[1, 1, 1, 1], padding='SAME')

h_conv3 = tf.nn.relu(conv3 + bias3)

# 全连接层

# 权值参数

W_fc1 = tf.Variable(tf.truncated_normal([7 * 7 * 120, 80]))

# 偏置值

b_fc1 = tf.Variable(tf.truncated_normal([80]))

# 将卷积的产出展开

h_pool2_flat = tf.reshape(h_conv3, [-1, 7 * 7 * 120])

# 神经网络计算，并添加relu激活函数

h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# 输出层，使用softmax进行多分类

W_fc2 = tf.Variable(tf.truncated_normal([80, 10]))

b_fc2 = tf.Variable(tf.truncated_normal([10]))

y_conv = tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2)

# 损失函数

cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))

# 使用GDO优化算法来调整参数

train_step = tf.train.GradientDescentOptimizer(0.0001).minimize(cross_entropy)

sess = tf.InteractiveSession()

# 测试正确率

correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

# 所有变量进行初始化

sess.run(tf.initialize_all_variables())

# 获取mnist数据

mnist_data_set = input_data.read_data_sets('F:\\TensorFlow_deep_learn\\MNIST\\', one_hot=True)

# 进行训练

start_time = time.time()

for i in range(20000):

    # 获取训练数据

    batch_xs, batch_ys = mnist_data_set.train.next_batch(200)

    # 每迭代100个 batch，对当前训练数据进行测试，输出当前预测准确率

    if i % 2 == 0:

        train_accuracy = accuracy.eval(feed_dict={x: batch_xs, y_: batch_ys})

        print("step %d, training accuracy %g" % (i, train_accuracy))

        # 计算间隔时间

        end_time = time.time()

        print('time: ', (end_time - start_time))

        start_time = end_time

    # 训练数据

    train_step.run(feed_dict={x: batch_xs, y_: batch_ys})

# 关闭会话

sess.close()

import time

import tensorflow as tf

import matplotlib.pyplot as plt

from tensorflow.examples.tutorials.mnist import input_data

def weight_variable(shape):

    initial = tf.truncated_normal(shape, stddev=0.1)

    return tf.Variable(initial)

#初始化单个卷积核上的偏置值

def bias_variable(shape):

    initial = tf.constant(0.1, shape=shape)

    return tf.Variable(initial)

#输入特征x，用卷积核W进行卷积运算，strides为卷积核移动步长，

#padding表示是否需要补齐边缘像素使输出图像大小不变

def conv2d(x, W):

    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

#对x进行最大池化操作，ksize进行池化的范围，

def max_pool_2x2(x):

    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')

sess = tf.InteractiveSession()

# 声明输入图片数据，类别

x = tf.placeholder('float32', [None, 784])

y_ = tf.placeholder('float32', [None, 10])

# 输入图片数据转化

x_image = tf.reshape(x, [-1, 28, 28, 1])

W_conv1 = weight_variable([5, 5, 1, 6])

b_conv1 = bias_variable([6])

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, 6, 16])

b_conv2 = bias_variable([16])

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*16,120])

# 偏置值

b_fc1 = bias_variable([120])

# 将卷积的产出展开

h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 16])

# 神经网络计算，并添加relu激活函数

h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

W_fc2 = weight_variable([120,10])

b_fc2 = bias_variable([10])

y_conv = tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2)

# 代价函数

cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))

# 使用Adam优化算法来调整参数

train_step = tf.train.GradientDescentOptimizer(1e-4).minimize(cross_entropy)

# 测试正确率

correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float32"))

# 所有变量进行初始化

sess.run(tf.initialize_all_variables())

# 获取mnist数据

mnist_data_set = input_data.read_data_sets('F:\\TensorFlow_deep_learn\\MNIST\\', one_hot=True)

c = []

# 进行训练

start_time = time.time()

for i in range(1000):

    # 获取训练数据

    batch_xs, batch_ys = mnist_data_set.train.next_batch(200)

    # 每迭代10个 batch，对当前训练数据进行测试，输出当前预测准确率

    if i % 2 == 0:

        train_accuracy = accuracy.eval(feed_dict={x: batch_xs, y_: batch_ys})

        c.append(train_accuracy)

        print("step %d, training accuracy %g" % (i, train_accuracy))

        # 计算间隔时间

        end_time = time.time()

        print('time: ', (end_time - start_time))

        start_time = end_time

    # 训练数据

    train_step.run(feed_dict={x: batch_xs, y_: batch_ys})

sess.close()

plt.plot(c)

plt.tight_layout()

plt.savefig('F:\\cnn-tf-cifar10-2.png', dpi=200)

plt.show()

import time

import tensorflow as tf

import matplotlib.pyplot as plt

from tensorflow.examples.tutorials.mnist import input_data

def weight_variable(shape):

    initial = tf.truncated_normal(shape, stddev=0.1)

    return tf.Variable(initial)

#初始化单个卷积核上的偏置值

def bias_variable(shape):

    initial = tf.constant(0.1, shape=shape)

    return tf.Variable(initial)

#输入特征x，用卷积核W进行卷积运算，strides为卷积核移动步长，

#padding表示是否需要补齐边缘像素使输出图像大小不变

def conv2d(x, W):

    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

#对x进行最大池化操作，ksize进行池化的范围，

def max_pool_2x2(x):

    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')

sess = tf.InteractiveSession()

# 声明输入图片数据，类别

x = tf.placeholder('float32', [None, 784])

y_ = tf.placeholder('float32', [None, 10])

# 输入图片数据转化

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])

# 偏置值

b_fc1 = bias_variable([1024])

# 将卷积的产出展开

h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])

# 神经网络计算，并添加relu激活函数

h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

W_fc2 = weight_variable([1024,10])

b_fc2 = bias_variable([10])

y_conv = tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2)

# 代价函数

cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))

# 使用Adam优化算法来调整参数

train_step = tf.train.GradientDescentOptimizer(1e-4).minimize(cross_entropy)

# 测试正确率

correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float32"))

# 所有变量进行初始化

sess.run(tf.initialize_all_variables())

# 获取mnist数据

mnist_data_set = input_data.read_data_sets('F:\\TensorFlow_deep_learn\\MNIST\\', one_hot=True)

c = []

# 进行训练

start_time = time.time()

for i in range(1000):

    # 获取训练数据

    batch_xs, batch_ys = mnist_data_set.train.next_batch(200)

    # 每迭代10个 batch，对当前训练数据进行测试，输出当前预测准确率

    if i % 2 == 0:

        train_accuracy = accuracy.eval(feed_dict={x: batch_xs, y_: batch_ys})

        c.append(train_accuracy)

        print("step %d, training accuracy %g" % (i, train_accuracy))

        # 计算间隔时间

        end_time = time.time()

        print('time: ', (end_time - start_time))

        start_time = end_time

    # 训练数据

    train_step.run(feed_dict={x: batch_xs, y_: batch_ys})

sess.close()

plt.plot(c)

plt.tight_layout()

plt.savefig('F:\\cnn-tf-cifar10-1.png', dpi=200)

plt.show()

import time

import tensorflow as tf

import matplotlib.pyplot as plt

from tensorflow.examples.tutorials.mnist import input_data

def weight_variable(shape):

    initial = tf.truncated_normal(shape, stddev=0.1)

    return tf.Variable(initial)

#初始化单个卷积核上的偏置值

def bias_variable(shape):

    initial = tf.constant(0.1, shape=shape)

    return tf.Variable(initial)

#输入特征x，用卷积核W进行卷积运算，strides为卷积核移动步长，

#padding表示是否需要补齐边缘像素使输出图像大小不变

def conv2d(x, W):

    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

#对x进行最大池化操作，ksize进行池化的范围，

def max_pool_2x2(x):

    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')

sess = tf.InteractiveSession()

# 声明输入图片数据，类别

x = tf.placeholder('float32', [None, 784])

y_ = tf.placeholder('float32', [None, 10])

# 输入图片数据转化

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])

# 偏置值

b_fc1 = bias_variable([1024])

# 将卷积的产出展开

h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])

# 神经网络计算，并添加relu激活函数

h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

W_fc2 = weight_variable([1024,128])

b_fc2 = bias_variable([128])

h_fc2 = tf.nn.relu(tf.matmul(h_fc1, W_fc2) + b_fc2)

W_fc3 = weight_variable([128,10])

b_fc3 = bias_variable([10])

y_conv = tf.nn.softmax(tf.matmul(h_fc2, W_fc3) + b_fc3)

# 代价函数

cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))

# 使用Adam优化算法来调整参数

train_step = tf.train.GradientDescentOptimizer(1e-5).minimize(cross_entropy)

# 测试正确率

correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float32"))

# 所有变量进行初始化

sess.run(tf.initialize_all_variables())

# 获取mnist数据

mnist_data_set = input_data.read_data_sets('F:\\TensorFlow_deep_learn\\MNIST\\', one_hot=True)

c = []

# 进行训练

start_time = time.time()

for i in range(1000):

    # 获取训练数据

    batch_xs, batch_ys = mnist_data_set.train.next_batch(200)

    # 每迭代10个 batch，对当前训练数据进行测试，输出当前预测准确率

    if i % 2 == 0:

        train_accuracy = accuracy.eval(feed_dict={x: batch_xs, y_: batch_ys})

        c.append(train_accuracy)

        print("step %d, training accuracy %g" % (i, train_accuracy))

        # 计算间隔时间

        end_time = time.time()

        print('time: ', (end_time - start_time))

        start_time = end_time

    # 训练数据

    train_step.run(feed_dict={x: batch_xs, y_: batch_ys})

sess.close()

plt.plot(c)

plt.tight_layout()

plt.savefig('F:\\cnn-tf-cifar10-11.png', dpi=200)

plt.show()

吴裕雄 python深度学习与实践（17）的更多相关文章

  1. 吴裕雄 python深度学习与实践（12）

    import tensorflow as tf q = tf.FIFOQueue(,"float32") counter = tf.Variable(0.0) add_op = t ...

  2. 吴裕雄 python深度学习与实践（18）

    # coding: utf-8 import time import numpy as np import tensorflow as tf import _pickle as pickle impo ...

  3. 吴裕雄 python深度学习与实践（16）

    import struct import numpy as np import matplotlib.pyplot as plt dateMat = np.ones((7,7)) kernel = n ...

  4. 吴裕雄 python深度学习与实践（15）

    import tensorflow as tf import tensorflow.examples.tutorials.mnist.input_data as input_data mnist = ...

  5. 吴裕雄 python深度学习与实践（14）

    import numpy as np import tensorflow as tf import matplotlib.pyplot as plt threshold = 1.0e-2 x1_dat ...

  6. 吴裕雄 python深度学习与实践（13）

    import numpy as np import matplotlib.pyplot as plt x_data = np.random.randn(10) print(x_data) y_data ...

  7. 吴裕雄 python深度学习与实践（11）

    import numpy as np from matplotlib import pyplot as plt A = np.array([[5],[4]]) C = np.array([[4],[6 ...

  8. 吴裕雄 python深度学习与实践（10）

    import tensorflow as tf input1 = tf.constant(1) print(input1) input2 = tf.Variable(2,tf.int32) print ...

  9. 吴裕雄 python深度学习与实践（9）

    import numpy as np import tensorflow as tf inputX = np.random.rand(100) inputY = np.multiply(3,input ...

随机推荐

  1. 详解java定时任务---Timer篇

    一.简介      在java的jdk中提供了Timer.TimerTask两个类来做定时任务. Timer是一种定时器工具,用来在一个后台线程计划执行指定任务,而TimerTask一个抽象类,它的子 ...

  2. CentOS7用yum快速搭建LAMP平台

    实验环境: [root@nmserver-7 html]# cat /etc/redhat-release CentOS release 7.3.1611 (AltArch) [root@nmserv ...

  3. 关于HTML和CSS一些鸡零狗碎的事

    原文发表于我自己的服务器www.jjxiaoliu.cn:不过这个服务器我可能不打算续费了,所以搬到cnblogs来. 有些关于HTML和CSS的内容不值得单独列一篇文章,全都放在这里了. 我们可以利 ...

  4. 使用COM打开Excel文档注意事项

    本文主要讲解程序中打开Excel文档,读写Excel文档可以参照前章: C#读写Excel实践笔记 C#使用NPOI读写Excel的注意事项 如果只是单纯的打开Excel文档,建议使用: System ...

  5. solr的基础使用

    查询运算符 例如:http://localhost:8984/solr/mycore/select?q=*:* :  指定字段查指定值,如返回所有值q=*:* ?  匹配单个字符, 例如: q=tit ...

  6. markdwon语法与Typora

    我也是在视频中看到别人的操作,不知道这是个什么玩意? 直到无意间看到了markdown,才意识到其他人用的是markdown. 当你看到一个人使用类似 ![blockchain](https://ss ...

  7. word 添加文本框

    转https://blog.csdn.net/sroco/article/details/17044973 如何在word2013(2007.2010)中添加带滚动条的文本框 2013年11月30日 ...

  8. 生成器函数_yield_yield from_send

    生成器函数 ''' yield类似于return 相同: 都返回出去一个值 不同: yield每次返回时, 会记录当前执行的位置 等下次调用生成器, 会从该位置向下走 return 直接终止函数 '' ...

  9. 【01】团饱和图：（一）EHM定理

    团饱和图:(一)EHM定理 据A. Hajnal考证,术语"饱和性",即saturation,最早由前苏联数学家A. A. Zykov在1949年引入,用于研究线性复形,但是他的工 ...

  10. windows下的Redis主从集群搭建

    Redis官方不提供Windows版本,目前Windows下的版本是有微软开源团队(Microsoft Open Tech group)维护. http://redis.cn/ redis中文网 wi ...