import struct

import  numpy as np

import matplotlib.pyplot as plt

dateMat = np.ones((7,7))

kernel = np.array([[2,1,1],[3,0,1],[1,1,0]])

def convolve(dateMat,kernel):

    m,n = dateMat.shape

    km,kn = kernel.shape

    newMat = np.ones(((m - km + 1),(n - kn + 1)))

    tempMat = np.ones(((km),(kn)))

    for row in range(m - km + 1):

        for col in range(n - kn + 1):

            for m_k in range(km):

                for n_k in range(kn):

                    tempMat[m_k,n_k] = dateMat[(row + m_k),(col + n_k)] * kernel[m_k,n_k]

            newMat[row,col] = np.sum(tempMat)

    return newMat

newMat = convolve(dateMat,kernel)

print(newMat)

import tensorflow as tf

input1 = tf.Variable(tf.random_normal([1, 3, 3, 1]))

filter1 = tf.Variable(tf.ones([1, 1, 1, 1]))

init = tf.global_variables_initializer()

with tf.Session() as sess:

    sess.run(init)

    conv2d = tf.nn.conv2d(input1, filter1, strides=[1, 1, 1, 1], padding='VALID')

    print(sess.run(conv2d))

import tensorflow as tf

input1 = tf.Variable(tf.random_normal([1, 5, 5, 5]))

filter1 = tf.Variable(tf.ones([3, 3, 5, 1]))

init = tf.global_variables_initializer()

with tf.Session() as sess:

    sess.run(init)

    conv2d = tf.nn.conv2d(input1, filter1, strides=[1, 1, 1, 1], padding='VALID')

    print(sess.run(conv2d))

import tensorflow as tf

input1 = tf.Variable(tf.random_normal([1, 5, 5, 5]))

filter1 = tf.Variable(tf.ones([3, 3, 5, 1]))

init = tf.global_variables_initializer()

with tf.Session() as sess:

    sess.run(init)

    conv2d = tf.nn.conv2d(input1, filter1, strides=[1, 1, 1, 1], padding='SAME')

    print(sess.run(conv2d))

import tensorflow as tf

input1 = tf.Variable(tf.random_normal([1, 5, 5, 5]))

filter1 = tf.Variable(tf.ones([3, 3, 5, 1]))

init = tf.global_variables_initializer()

with tf.Session() as sess:

    sess.run(init)

    conv2d = tf.nn.conv2d(input1, filter1, strides=[1, 2, 2, 1], padding='SAME')

    print(sess.run(conv2d))

import cv2

import numpy as np

import tensorflow as tf

img = cv2.imread("D:\\F\\TensorFlow_deep_learn\\data\\lena.jpg")

img = np.array(img,dtype=np.float32)

x_image=tf.reshape(img,[1,512,512,3])

filter1 = tf.Variable(tf.ones([7, 7, 3, 1]))

init = tf.global_variables_initializer()

with tf.Session() as sess:

    sess.run(init)

    res = tf.nn.conv2d(x_image, filter1, strides=[1, 2, 2, 1], padding='SAME')

    res_image = sess.run(tf.reshape(res,[256,256]))/128 + 1

cv2.imshow("lover",res_image.astype('uint8'))

cv2.waitKey()
import cv2

import numpy as np

import tensorflow as tf

img = cv2.imread("D:\\F\\TensorFlow_deep_learn\\data\\lena.jpg")

img = np.array(img,dtype=np.float32)

x_image=tf.reshape(img,[1,512,512,3])

filter1 = tf.Variable(tf.ones([11, 11, 3, 1]))

init = tf.global_variables_initializer()

with tf.Session() as sess:

    sess.run(init)

    res = tf.nn.conv2d(x_image, filter1, strides=[1, 2, 2, 1], padding='SAME')

    res_image = sess.run(tf.reshape(res,[256,256]))/128 + 1

cv2.imshow("lover",res_image.astype('uint8'))

cv2.waitKey()
import tensorflow as tf

data=tf.constant([

        [[3.0,2.0,3.0,4.0],

        [2.0,6.0,2.0,4.0],

        [1.0,2.0,1.0,5.0],

        [4.0,3.0,2.0,1.0]]

        ])

data = tf.reshape(data,[1,4,4,1])

maxPooling=tf.nn.max_pool(data, [1, 2, 2, 1], [1, 2, 2, 1], padding='VALID')

with tf.Session() as sess:

    print(sess.run(maxPooling))

import cv2

import numpy as np

import tensorflow as tf

img = cv2.imread("D:\\F\\TensorFlow_deep_learn\\data\\lena.jpg")

img = np.array(img,dtype=np.float32)

x_image=tf.reshape(img,[1,512,512,3])

filter1 = tf.Variable(tf.ones([7, 7, 3, 1]))

init = tf.global_variables_initializer()

with tf.Session() as sess:

    sess.run(init)

    res = tf.nn.conv2d(x_image, filter1, strides=[1, 2, 2, 1], padding='SAME')

    res = tf.nn.max_pool(res, [1, 2, 2, 1], [1, 2, 2, 1], padding='VALID')

    res_image = sess.run(tf.reshape(res,[128,128]))/128 + 1

cv2.imshow("lover",res_image.astype('uint8'))

cv2.waitKey()
import time

import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data

# 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.sigmoid(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.sigmoid(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.sigmoid(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sigmoid激活函数

h_fc1 = tf.nn.sigmoid(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(0.001).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("D:\\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

from tensorflow.examples.tutorials.mnist import input_data

# 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(0.001).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("D:\\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()

吴裕雄 python深度学习与实践（16）的更多相关文章

  1. 吴裕雄 python深度学习与实践（17）

    import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import time # 声明输 ...

  2. 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 ...

  3. 吴裕雄 python深度学习与实践（5）

    import numpy as np data = np.mat([[1,200,105,3,False], [2,165,80,2,False], [3,184.5,120,2,False], [4 ...

  4. 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 ...

  5. 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 = ...

  6. 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 ...

  7. 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 ...

  8. 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 ...

  9. 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 ...

随机推荐

  1. 定义action的允许访问方式

    publicfunction behaviors() { return[ 'verbs'=>[ 'class'=>VerbFilter::className(), 'actions'=&g ...

  2. python中序列化模块json和pickle

    json模块:json是第三方包,不是系统内置模块,以字符串序列 常用操作有: json.dumps() # 将变量序列化,即将功能性字符转化为字符串 例: >>> import j ...

  3. "Error: [$compile:multidir] Multiple directives

    angularjs 中控制台报"Error: [$compile:multidir] Multiple directives错误 可以在当前html元素之上增加父元素,在父元素中加入第二个指 ...

  4. 面向对象+JAVA基础

    泛泛的研究了面向对象的前五章,感觉没有代码的参照理解的知识看过就忘,所以又在推荐下开始了JAVA基础,希望不会鄙视我目前么有一本书能完整看完的记录... public class LeapYear { ...

  5. PythonStudy——字符串常用操作 String common operations

    # 1.字符串的索引取值: 字符串[index]# 正向取值从0编号,反向取值从-1编号 s1 = '123abc呵呵' t_s = ' # 取出c print(s1[5], s1[-3]) # 2. ...

  6. linux下一些重要命令的了解

    linux下一些比较重要的命令: du命令: 查看使用空间: 格式: du [选项][文件] 参数: -a  显示目录中个别文件的大小. -b  显示目录或文件大小时,以byte为单位. -c  除了 ...

  7. c# 判断时间是否在 某一时间段内

    protected bool getTimeSpan(string timeStr) { //判断当前时间是否在工作时间段内 string _strWorkingDayAM = "08:30 ...

  8. 利用STM32CubeMX来生成USB_HID_Mouse工程【添加ADC】（2）【非dma和中断方式】

    上回讲到怎么采集一路的adc的数据,这次我们来采集两路的数据. 现在直接修改原先的代码 /* Private variables ----------------------------------- ...

  9. PHP 获取数组是几维数组

    // 判断数组是几维数组$data = array(); // 是你要判断的数组$al = array(0);function aL($data,&$al,$level=0){ if(is_a ...

  10. 队列&广搜

    搜索里有深搜,又有广搜,而广搜的基础就是队列. 队列是一种特殊的线性表,只能在一段插入,另一端输出.输出的那一端叫做队头,输入的那一端叫队尾.是一种先进先出(FIFO)的数据结构. 正经的队列: 头文 ...