将自己的数据集转换为cifar数据集格式(改进)

2022/8/6 23:22:57

本文主要是介绍将自己的数据集转换为cifar数据集格式(改进),对大家解决编程问题具有一定的参考价值,需要的程序猿们随着小编来一起学习吧!

cifar数据集的基本情况:

该数据集共有60000张彩色图像,这些图像是32*32,分为10个类,每类6000张图。这里面有50000张用于训练,构成了5个训练批,每一批10000张图;另外10000用于测试,单独构成一批。测试批的数据里,取自10类中的每一类,每一类随机取1000张。抽剩下的就随机排列组成了训练批。注意一个训练批中的各类图像并不一定数量相同,总的来看训练批,每一类都有5000张图。

 

 我们可以看到下载后的数据集文件夹包括:

 

 其中data_batch就是用于训练的数据集,一共有五个;test_batch就是用于测试的数据集,一共有一个;batchs.meta其中包含的信息是类别名称,下面我们就仔细看看各个文件包含的具体内容:

各文件详细内容

  • 1. batch.meta

 

import pickle
 
def unpickle(file):
    with open(file, 'rb') as fo:
        dict = pickle.load(fo, encoding='latin-1')
    return dict
cc=unpickle("./dataset/cifar-10/cifar-10-batches-py/batches.meta") #路径需要自行修改
print(cc)

运行结果:

 

 可以看到:batch应该是一个batch包含的图片数量,label_names应该是类别名字,num_vis应该是32*32(图片大小)*3(RGB三通道),个人理解为描述一副图像所需要的值。

  • 2. data_batch_1

debug结果:代码不加赘述,上面的改下路径就行

 

 可以看到,其中包含batch_label,labels,data,filenames四项,其中batch_label就是第几个batch,labels就是第几类,data就是上面3072对应的具体值啦(不止一个3017,因为不止一幅图,大家自行理解哈),其实就是RGB值,filename就是图片的名字,是不是挺简单的。test_batch也是一样的样的道理。

 

接下来就是具体自己的数据集转换的代码:

# -*- coding: utf-8 -*-
"""
@author: zhangjiaqing 有借鉴
"""
import numpy as np
import chardet
from PIL import Image
import operator
from os import listdir
import sys
import pickle
import random
 
def unpickle(file):
    with open(file, 'rb') as fo:
        dict = pickle.load(fo, encoding='latin-1')
    return dict
#cc=unpickle("./dataset/cifar-10/cifar-10-batches-py/data_batch_1")
#print(cc)
 
data={}
list1=[]
list2=[]
list3=[]
#将图片转化为32*32的三通道图片
def img_tra():
    for k in range(0,num):
        currentpath=folder+"/"+imglist[k]
        im=Image.open(currentpath)
        #width=im.size[0]
        #height=im.size[1]
        x_s=32
        y_s=32
        out = im.resize((x_s,y_s),Image.ANTIALIAS)
        out.save(folder_ad+"/"+str(imglist[k]))
 
def addWord(theIndex,word,adder):
    theIndex.setdefault(word,[]).append(adder)
def seplabel(fname):
    filestr=fname.split(".")[0]
    label=int(filestr.split("_")[0]) #图片的命名 _前面是类别
    return label
def mkcf():
    global data
    global list1
    global list2
    global list3
    for k in range(0,num):
        currentpath=folder_ad+"/"+imglist[k]
        im=Image.open(currentpath)
        with open(binpath, 'a') as f:
            for i in range (0,32):
                for j in range (0,32):
                    cl=im.getpixel((i,j))
                    list1.append(cl[0])  #R
 
            for i in range (0,32):
                for j in range (0,32):
                    cl=im.getpixel((i,j))
                    #with open(binpath, 'a') as f:
                    #mid=str(cl[1])
                    #f.write(mid)
                    list1.append(cl[1]) #G
 
            for i in range (0,32):
                for j in range (0,32):
                    cl=im.getpixel((i,j))
                    list1.append(cl[2]) ##B
        list2.append(list1)
        list1=[]
        f.close()
        print("image"+str(k+1)+"saved.")
        list3.append(imglist[k])    #name of pictures
    arr2=np.array(list2,dtype=np.uint8)
    data['batch_label']='training batch 5 of 5' #training batch 1 of 5 testing batch 1 of 1
    data.setdefault('labels',label)
    data.setdefault('data',arr2)
    data.setdefault('filenames',list3)
    output = open(binpath, 'wb')
    pickle.dump(data, output)
    output.close()
 
folder="./cloud/train_batch_5"  #自己图片的路径 train_batch_5 test
folder_ad="./cloud/train_batch_5_ad" #将图片转化为32*32的三通道图片的路径  train_batch_5_ad test_ad
imglist=listdir(folder) #这里原作者好像写错了,我自行修改了,目测现在是对的
num=len(imglist)
img_tra()
label=[]
for i in range (0,num):
    label.append(seplabel(imglist[i]))
binpath="./dataset/cloud/cloud-5-batches-py/data_batch_5" #保存的路径 data_batch_5 test_batch
print(binpath)
mkcf()

  给大家看一下转的结果

 

 解释一下为什么这里少了batch.meta,感觉这里的信息没什么用,如果是自己的数据集,可以直接写一句代码就行: 

classes = ['A', 'B', 'C', 'D', 'E']

  注意自己数据集图片的命名:‘_‘前面是类别

 

 

代码改进:训练测试集路径不用一直修改

# -*- coding: utf-8 -*-
"""
@author: zhangjiaqing
"""
import numpy as np
import chardet
from PIL import Image
import operator
from os import listdir
import sys
import pickle
import random
from skimage.util.shape import view_as_windows
 
def unpickle(file):
    with open(file, 'rb') as fo:
        dict = pickle.load(fo, encoding='latin-1')
    return dict
#cc=unpickle("./dataset/cloud/cloud-5-batches-py/test_batch")
#cc=unpickle("./dataset/cifar-10\cifar-10-batches-py/data_batch_1")
 
#print(cc)
 
data = {}
list1 = []
list2 = []
list3 = []
label = []
size = 64
def split():
    global label
    for k in range(0,num):
        currentpath=folder+imglist[k]
        img=Image.open(currentpath)
        img = np.array(img)
        img_block_2 = view_as_windows(img, (size, size, 3), step=size)
        hang = img_block_2.shape[0]
        lie = img_block_2.shape[1]
        label=[]
        img_block = np.zeros((size,size,3))
        for i in range (hang):
            for j in range(lie):
                label.append(random.randint(0, 4))
                img_block = img_block_2[i,j,0,:,:,:]
                image = Image.fromarray(img_block.astype('uint8'))
                image.save(folder_ad + '%s_%d_%d.jpg'%(str(imglist[k]),i*lie+j,label[i*lie+j]))
        #out.save(folder_ad+"/"+str(imglist[k]))
 
def addWord(theIndex,word,adder):
    theIndex.setdefault(word,[]).append(adder)
 
def mkcf():
    global data
    global list1
    global list2
    global list3
    global train
    for k in range(0,number):
        currentpath=folder_ad+imagelist[k]
        im=Image.open(currentpath)
        with open(binpath, 'a') as f:
            for i in range (0,size):
                for j in range (0,size):
                    cl=im.getpixel((i,j))
                    list1.append(cl[0])  #R
 
            for i in range (0,size):
                for j in range (0,size):
                    cl=im.getpixel((i,j))
                    list1.append(cl[1]) #G
 
            for i in range (0,size):
                for j in range (0,size):
                    cl=im.getpixel((i,j))
                    list1.append(cl[2]) ##B
        list2.append(list1)
        list1=[]
        f.close()
        print("image"+str(k+1)+"saved.")
        list3.append(imagelist[k])    #name of pictures
    arr2=np.array(list2,dtype=np.uint8)
    if train:
        data['batch_label']='training batch 1 of 1' #training batch 1 of 5 testing batch 1 of 1
    else:
        data['batch_label']='testing batch 1 of 1' #training batch 1 of 5 testing batch 1 of 1
    data.setdefault('labels',label)
    data.setdefault('data',arr2)
    data.setdefault('filenames',list3)
    output = open(binpath, 'wb')
    pickle.dump(data, output)
    output.close()
 
train = False #true就是训练集路径 #false就是测试集路径
if train:
    folder="./cloud/train_batch_1/"  # train_batch_5 test
    folder_ad="./cloud/train_batch_1_ad/" #将图片转化为32*32的三通道图片  train_batch_5_ad test_ad
    binpath="./dataset/cloud/cloud-5-batches-py/data_batch_1" # data_batch_5 test_batch
else:
    folder="./cloud/test/"  # train_batch_5 test
    folder_ad="./cloud/test_ad/" #将图片转化为32*32的三通道图片  train_batch_5_ad test_ad
    binpath="./dataset/cloud/cloud-5-batches-py/test_batch" # data_batch_5 test_batch
 
imglist=listdir(folder)
num=len(imglist)
split()
 
imagelist=listdir(folder_ad)
number=len(imagelist)
mkcf()
print('the work is finished!')

  



这篇关于将自己的数据集转换为cifar数据集格式(改进)的文章就介绍到这儿,希望我们推荐的文章对大家有所帮助,也希望大家多多支持为之网!


扫一扫关注最新编程教程