文字识别

文字识别

更多干货

• 分布式实战（干货）

• spring cloud 实战（干货）

• mybatis 实战（干货）

• spring boot 实战（干货）

• React 入门实战（干货）

• 构建中小型互联网企业架构（干货）

• python 学习持续更新

• ElasticSearch 笔记

• kafka storm 实战 (干货)

• scala 学习持续更新

• RPC

• 深度学习

概述

样本地址

http://yann.lecun.com/exdb/mnist/

KNN代码

# 1 重要
# 2 KNN CNN 2种
# 3 样本
# 4 旧瓶装新酒 ：数字识别的不同
# 4.1 网络 4。2 每一级 4.3 先原理 后代码
# 本质：knn test 样本 K个 max4 3个1 -》1

# 1 load Data  1.1 随机数 1.2 4组 训练 测试 （图片 和 标签）
# 2 knn test train distance 5*500 = 2500 784=28*28
# 3 knn k个最近的图片5 500 1-》500train （4）
# 4 k个最近的图片-> parse centent label
# 5 label -》 数字 p9 测试图片-》数据
# 6 检测概率统计
import tensorflow as tf
import numpy as np
import random
from tensorflow.examples.tutorials.mnist import input_data
# load data 2 one_hot : 1 0000 1 fileName
mnist = input_data.read_data_sets('MNIST_data',one_hot=True)
# 属性设置
trainNum = 55000
testNum = 10000
trainSize = 500
testSize = 5
k = 4
# data 分解 1 trainSize   2范围0-trainNum 3 replace=False
trainIndex = np.random.choice(trainNum,trainSize,replace=False)
testIndex = np.random.choice(testNum,testSize,replace=False)
trainData = mnist.train.images[trainIndex]# 训练图片
trainLabel = mnist.train.labels[trainIndex]# 训练标签
testData = mnist.test.images[testIndex]
testLabel = mnist.test.labels[testIndex]
# 28*28 = 784
print('trainData.shape=',trainData.shape)#500*784 1 图片个数 2 784?
print('trainLabel.shape=',trainLabel.shape)#500*10
print('testData.shape=',testData.shape)#5*784
print('testLabel.shape=',testLabel.shape)#5*10
print('testLabel=',testLabel)# 4 :testData [0]  3:testData[1] 6
# tf input  784->image
trainDataInput = tf.placeholder(shape=[None,784],dtype=tf.float32)
trainLabelInput = tf.placeholder(shape=[None,10],dtype=tf.float32)
testDataInput = tf.placeholder(shape=[None,784],dtype=tf.float32)
testLabelInput = tf.placeholder(shape=[None,10],dtype=tf.float32)
#knn distance 5*785.  5*1*784
# 5 500 784 (3D) 2500*784
f1 = tf.expand_dims(testDataInput,1) # 维度扩展
f2 = tf.subtract(trainDataInput,f1)# 784 sum(784)
f3 = tf.reduce_sum(tf.abs(f2),reduction_indices=2)# 完成数据累加 784 abs
# 5*500
f4 = tf.negative(f3)# 取反
f5,f6 = tf.nn.top_k(f4,k=4) # 选取f4 最大的四个值
# f3 最小的四个值
# f6 index->trainLabelInput
f7 = tf.gather(trainLabelInput,f6)
# f8 num reduce_sum  reduction_indices=1 '竖直'
f8 = tf.reduce_sum(f7,reduction_indices=1)
# tf.argmax 选取在某一个最大的值 index
f9 = tf.argmax(f8,dimension=1)
# f9 -> test5 image -> 5 num
with tf.Session() as sess:
    # f1 <- testData 5张图片
    p1 = sess.run(f1,feed_dict={testDataInput:testData[0:5]})
    print('p1=',p1.shape)# p1= (5, 1, 784)
    p2 = sess.run(f2,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5]})
    print('p2=',p2.shape)#p2= (5, 500, 784) (1,100)
    p3 = sess.run(f3,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5]})
    print('p3=',p3.shape)#p3= (5, 500)
    print('p3[0,0]=',p3[0,0]) #130.451 knn distance p3[0,0]= 155.812

    p4 = sess.run(f4,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5]})
    print('p4=',p4.shape)
    print('p4[0,0]',p4[0,0])

    p5,p6 = sess.run((f5,f6),feed_dict={trainDataInput:trainData,testDataInput:testData[0:5]})
    #p5= (5, 4) 每一张测试图片（5张）分别对应4张最近训练图片
    #p6= (5, 4)
    print('p5=',p5.shape)
    print('p6=',p6.shape)
    print('p5[0,0]',p5[0])
    print('p6[0,0]',p6[0])# p6 index

    p7 = sess.run(f7,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5],trainLabelInput:trainLabel})
    print('p7=',p7.shape)#p7= (5, 4, 10)
    print('p7[]',p7)

    p8 = sess.run(f8,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5],trainLabelInput:trainLabel})
    print('p8=',p8.shape)
    print('p8[]=',p8)

    p9 = sess.run(f9,feed_dict={trainDataInput:trainData,testDataInput:testData[0:5],trainLabelInput:trainLabel})
    print('p9=',p9.shape)
    print('p9[]=',p9)

    p10 = np.argmax(testLabel[0:5],axis=1)
    print('p10[]=',p10)
j = 0
for i in range(0,5):
    if p10[i] == p9[i]:
        j = j+1
print('ac=',j*100/5)

CNN

#cnn : 1 卷积
# ABC
# A: 激励函数+矩阵 乘法加法
# A CNN :  pool（激励函数+矩阵 卷积 加法）
# C：激励函数+矩阵 乘法加法（A-》B）
# C：激励函数+矩阵 乘法加法（A-》B） + softmax（矩阵 乘法加法）
# loss：tf.reduce_mean(tf.square(y-layer2))
# loss：code
#1 import
import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
# 2 load data
mnist = input_data.read_data_sets('MNIST_data',one_hot = True)
# 3 input
imageInput = tf.placeholder(tf.float32,[None,784]) # 28*28
labeInput = tf.placeholder(tf.float32,[None,10]) # knn
# 4 data reshape
# [None,784]->M*28*28*1  2D->4D  28*28 wh 1 channel
imageInputReshape = tf.reshape(imageInput,[-1,28,28,1])
# 5 卷积 w0 : 卷积内核 5*5 out:32  in:1
w0 = tf.Variable(tf.truncated_normal([5,5,1,32],stddev = 0.1))
b0 = tf.Variable(tf.constant(0.1,shape=[32]))
# 6 # layer1：激励函数+卷积运算
# imageInputReshape : M*28*28*1  w0:5,5,1,32
layer1 = tf.nn.relu(tf.nn.conv2d(imageInputReshape,w0,strides=[1,1,1,1],padding='SAME')+b0)
# M*28*28*32
# pool 采样 数据量减少很多M*28*28*32 => M*7*7*32
layer1_pool = tf.nn.max_pool(layer1,ksize=[1,4,4,1],strides=[1,4,4,1],padding='SAME')
# [1 2 3 4]->[4]
# 7 layer2 out : 激励函数+乘加运算：  softmax（激励函数 + 乘加运算）
# [7*7*32,1024]
w1 = tf.Variable(tf.truncated_normal([7*7*32,1024],stddev=0.1))
b1 = tf.Variable(tf.constant(0.1,shape=[1024]))
h_reshape = tf.reshape(layer1_pool,[-1,7*7*32])# M*7*7*32 -> N*N1
# [N*7*7*32]  [7*7*32,1024] = N*1024
h1 = tf.nn.relu(tf.matmul(h_reshape,w1)+b1)
# 7.1 softMax
w2 = tf.Variable(tf.truncated_normal([1024,10],stddev=0.1))
b2 = tf.Variable(tf.constant(0.1,shape=[10]))
pred = tf.nn.softmax(tf.matmul(h1,w2)+b2)# N*1024  1024*10 = N*10
# N*10( 概率 )N1【0.1 0.2 0.4 0.1 0.2 。。。】
# label。        【0 0 0 0 1 0 0 0.。。】
loss0 = labeInput*tf.log(pred)
loss1 = 0
# 7.2
for m in range(0,500):#  test 100
    for n in range(0,10):
        loss1 = loss1 - loss0[m,n]
loss = loss1/500

# 8 train
train = tf.train.GradientDescentOptimizer(0.01).minimize(loss)
# 9 run
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(100):
        images,labels = mnist.train.next_batch(500)
        sess.run(train,feed_dict={imageInput:images,labeInput:labels})

        pred_test = sess.run(pred,feed_dict={imageInput:mnist.test.images,labeInput:labels})
        acc = tf.equal(tf.arg_max(pred_test,1),tf.arg_max(mnist.test.labels,1))
        acc_float = tf.reduce_mean(tf.cast(acc,tf.float32))
        acc_result = sess.run(acc_float,feed_dict={imageInput:mnist.test.images,labeInput:mnist.test.labels})
        print(acc_result)