图像处理基本库的学习笔记2--SVM，MATLAB，Tensorflow下分别对mnist数据集进行训练，并且进行预测

目录

• SVM
• MATLAB
• Tensorflow

SVM

支持向量机（Support Vector Machine, SVM）是一类按监督学习（supervised learning）方式对数据进行二元分类（binary classification）的广义线性分类器（generalized linear classifier），其决策边界是对学习样本求解的最大边距超平面（maximum-margin hyperplane）

**流程
1. 收集数据：此处使用给定的文本文件
2. 准备数据：基于二值图像构造数据
3. 分析数据：对图像向量进行目测
4. 训练算法：采用三种不同的方法，不同的参数 线性分类器二次多项式核函数径向基核函数
5. 测试并计算错误率

以下直接使用sklearn.svm模块中的算法库对mnist数据集进行训练，并且进行预测：

import numpy as np
import struct
import matplotlib.pyplot as plt
import osimport pickle

##加载svm模型
from sklearn import svm

###用于做数据预处理
from sklearn import preprocessing
import time

##读取数据集
path='E:\\数据挖掘\\MNIST_data'
def load_mnist_train(path, kind='train'):
labels_path = os.path.join(path,'%s-labels.idx1-ubyte'% kind)
images_path = os.path.join(path,'%s-images.idx3-ubyte'% kind)
with open(labels_path, 'rb') as lbpath:
magic, n = struct.unpack('>II',lbpath.read(8))
labels = np.fromfile(lbpath,dtype=np.uint8)
with open(images_path, 'rb') as imgpath:
magic, num, rows, cols = struct.unpack('>IIII',imgpath.read(16))
images = np.fromfile(imgpath,dtype=np.uint8).reshape(len(labels), 784)
return images, labels
def load_mnist_test(path, kind='t10k'):
labels_path = os.path.join(path,'%s-labels.idx1-ubyte'% kind)
images_path = os.path.join(path,'%s-images.idx3-ubyte'% kind)
with open(labels_path, 'rb') as lbpath:
magic, n = struct.unpack('>II',lbpath.read(8))
labels = np.fromfile(lbpath,dtype=np.uint8)
with open(images_path, 'rb') as imgpath:
magic, num, rows, cols = struct.unpack('>IIII',imgpath.read(16))
images = np.fromfile(imgpath,dtype=np.uint8).reshape(len(labels), 784)
return images, labels
train_images,train_labels=load_mnist_train(path)
test_images,test_labels=load_mnist_test(path)

##标准化
X=preprocessing.StandardScaler().fit_transform(train_images)
X_train=X[0:60000]
y_train=train_labels[0:60000]

##定义并训练模型
print(time.strftime('%Y-%m-%d %H:%M:%S'))
model_svc = svm.SVC()
model_svc.fit(X_train,y_train)
print(time.strftime('%Y-%m-%d %H:%M:%S'))##保存模型
file = open("model.pickle", "wb")
pickle.dump(model_svc, file)
file.close()

##读取模型
file = open("model.pickle", "rb")
model_svc = pickle.load(file)
file.close()

##评分并预测
x=preprocessing.StandardScaler().fit_transform(test_images)
x_test=x[0:10000]
y_pred=test_labels[0:10000]
print(model_svc.score(x_test,y_pred))
y=model_svc.predict(x_test)

训练用时将近12分钟

测试输出正确率：96.57%

输出预测结果：可知结果均正确

MATLAB

自动识别MNIST手写数字数据库

在命令行运行cnet tool，出现GUI界面，选择t10k-images.idx3-ubyte。

直接手写测试也是正确的

Tensorflow

用tensorflow识别，效果依旧很好

训练模型

from tensorflow.examples.tutorials.mnist import input_data

import tensorflow as tf

mnist = input_data.read_data_sets('E:\数据挖掘\MNIST_data', one_hot=True) #MNIST数据集所在路径

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

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

def weight_variable(shape):
initial = tf.truncated_normal(shape,stddev = 0.1)
return tf.Variable(initial)

def bias_variable(shape):
initial = tf.constant(0.1,shape = shape)
return tf.Variable(initial)

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

def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

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

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])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

saver = tf.train.Saver() #定义saver

with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(600):
batch = mnist.train.next_batch(50)
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x: batch[0], y_: batch[1], keep_prob: 1.0})
print('step %d, training accuracy %g' % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
saver.save(sess, 'C:/Users/YUANMU/PycharmProjects/tensorflow') #模型储存位置

print('test accuracy %g' % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

测试模型

from PIL import Image, ImageFilter
import tensorflow as tf
import matplotlib.pyplot as plt

def imageprepare():
im = Image.open('C:/Users/YUANMU/PycharmProjects/tensorflow/4.png') #读取的图片所在路径，注意是28*28像素
plt.imshow(im)  #显示需要识别的图片
plt.show()
im = im.convert('L')
tv = list(im.getdata())
tva = [(255-x)*1.0/255.0 for x in tv]
return tva

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

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

def weight_variable(shape):
initial = tf.truncated_normal(shape,stddev = 0.1)
return tf.Variable(initial)

def bias_variable(shape):
initial = tf.constant(0.1,shape = shape)
return tf.Variable(initial)

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

def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

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

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])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

saver = tf.train.Saver()

with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, "C:/Users/YUANMU/PycharmProjects/tensorflow") #使用模型，参数和之前的代码保持一致

prediction=tf.argmax(y_conv,1)
predint=prediction.eval(feed_dict={x: [result],keep_prob: 1.0}, session=sess)

print('识别结果:')
print(predint[0])

• 点赞
• 收藏
• 分享
• 文章举报