预处理（1）遗传病人脸数据统计

1.代码

import os

path0 ="E:\\apache-tomcat-8.0.30\\webapps\\ImageSearch\\PidiPalace\\image"

path="E:\\research\\data\\Hypertelorism-20180710\\Picture"
txtPath="E:\\research\\data\\Hypertelorism-20180710\\static.txt"


if os.path.exists(txtPath):
    print("666")
else:
    print("creat train resize")

f =open(txtPath,"w")
#path = os.getcwd()+'/data/train/'
count = 0
filename=[]
num=[]
repeat=1
for file in os.listdir(path) :
        count = count + 1
        print(file[0:-5])
        #ff='/'+filename+"/"+file+" "+filename+"\n"
        if count == 1:
            print("666")
            filename.append(file)
            print(filename)
            continue
        elif filename[-1][0:-5]==file[0:-5]:
            repeat=repeat+1
            continue
        else:
            filename.append(file)
        num.append(repeat)
        print(num)
        repeat = 1
        temp = file
        ff = file + " " + "\n"
        f.write(ff)
        print ('{} class: {}'.format(file,count))
f.close()
num.append(repeat)
print(num)
print(sum(num))
print("遗传疾病种类数：",len(num))
num1=0
for i in range(5):
   print("图片数为"+str(i+1)+"的遗传病类别数："+str(num.count(i+1)))
   num1 = num1+num.count(i+1)*(i+1)
print(num1)

2. 实验结果

遗传疾病种类数： 190
图片数为1的遗传病类别数：30
图片数为2的遗传病类别数：29
图片数为3的遗传病类别数：33
图片数为4的遗传病类别数：25
图片数为5的遗传病类别数：73
652