目标检测-数据处理，YOLO2JSON、VOC2YOLO、YOLO2VOC、JSON2YOLO

1、YOLO格式转JSON格式

"""

YOLO转JSON格式

"""

import os
import cv2
import json
import argparse
from tqdm import tqdm
import xml.etree.ElementTree as ET

COCO_DICT=['images','annotations','categories']
IMAGES_DICT=['file_name','height','width','id']

ANNOTATIONS_DICT=['image_id','iscrowd','area','bbox','category_id','id']

CATEGORIES_DICT=['id','name']

#自定义YOLO数据集类别
YOLO_CATEGORIES=['Cahua', 'Crazing']

parser=argparse.ArgumentParser(description='2COCO')
#需修改：图片所在路径
parser.add_argument('--image_path',type=str,default=r'D:\desk\defect_dataset\images\test/',help='config file')

#需修改：标签所在路径
parser.add_argument('--annotation_path',type=str,default=r'D:\desk\defect_dataset\labels\test/',help='config file')

parser.add_argument('--dataset',type=str,default='YOLO',help='config file')

#需修改：JSON文件保存位置
parser.add_argument('--save',type=str,default=r'D:\desk\defect_dataset\JASON/instances_test2017.json',help='config file')
args=parser.parse_args()
def load_json(path):
	with open(path,'r') as f:
		json_dict=json.load(f)
		for i in json_dict:
			print(i)
		print(json_dict['annotations'])
def save_json(dict,path):
	print('SAVE_JSON...')
	with open(path,'w') as f:
		json.dump(dict,f)
	print('SUCCESSFUL_SAVE_JSON:',path)
def load_image(path):
	img=cv2.imread(path)
	return img.shape[0],img.shape[1]
def generate_categories_dict(category):       #ANNOTATIONS_DICT=['image_id','iscrowd','area','bbox','category_id','id']
	print('GENERATE_CATEGORIES_DICT...')
	return [{CATEGORIES_DICT[0]:category.index(x)+1,CATEGORIES_DICT[1]:x} for x in category]  #CATEGORIES_DICT=['id','name']
def generate_images_dict(imagelist,image_path,start_image_id=11725):  #IMAGES_DICT=['file_name','height','width','id']
	print('GENERATE_IMAGES_DICT...')
	images_dict=[]
	with tqdm(total=len(imagelist)) as load_bar:
		for x in imagelist:  #x就是图片的名称
			#print(start_image_id)
			dict={IMAGES_DICT[0]:x,IMAGES_DICT[1]:load_image(image_path+x)[0],\
					IMAGES_DICT[2]:load_image(image_path+x)[1],IMAGES_DICT[3]:imagelist.index(x)+start_image_id}
			load_bar.update(1)
			images_dict.append(dict)
	return images_dict

def YOLO_Dataset(image_path,annotation_path,start_image_id=0,start_id=0):
	categories_dict=generate_categories_dict(YOLO_CATEGORIES)
	imgname=os.listdir(image_path)
	images_dict=generate_images_dict(imgname,image_path)
	print('GENERATE_ANNOTATIONS_DICT...')
	annotations_dict=[]
	id=start_id
	for i in images_dict:
		image_id=i['id']
		image_name=i['file_name']
		W,H=i['width'],i['height']
		annotation_txt=annotation_path+image_name.split('.')[0]+'.txt'
		txt=open(annotation_txt,'r')
		lines=txt.readlines()
		for j in lines:
			category_id=int(j.split(' ')[0])+1
			category=YOLO_CATEGORIES
			x=float(j.split(' ')[1])
			y=float(j.split(' ')[2])
			w=float(j.split(' ')[3])
			h=float(j.split(' ')[4])
			x_min=(x-w/2)*W
			y_min=(y-h/2)*H
			w=w*W
			h=h*H
			area=w*h
			bbox=[x_min,y_min,w,h]
			dict={'image_id':image_id,'iscrowd':0,'area':area,'bbox':bbox,'category_id':category_id,'id':id}
			annotations_dict.append(dict)
			id=id+1
	print('SUCCESSFUL_GENERATE_YOLO_JSON')
	return {COCO_DICT[0]:images_dict,COCO_DICT[1]:annotations_dict,COCO_DICT[2]:categories_dict}

if __name__=='__main__':
	dataset=args.dataset   #数据集名字
	save=args.save  #json的保存路径
	image_path=args.image_path     #对于coco是图片的路径
	annotation_path=args.annotation_path   #coco的annotation路径
	if dataset=='YOLO':
		json_dict=YOLO_Dataset(image_path,annotation_path,0)
	save_json(json_dict,save)

 上述代码中仅需要修改以下部分，再运行即可完成YOLO格式转换为JSON格式。

23行
#自定义YOLO数据集类别
YOLO_CATEGORIES=['Cahua', 'Crazing']

27行
#需修改：图片所在路径
parser.add_argument('--image_path',type=str,default=r'D:\desk\defect_dataset\images\test/',help='config file')

30行
#需修改：标签所在路径
parser.add_argument('--annotation_path',type=str,default=r'D:\desk\defect_dataset\labels\test/',help='config file')

35行
parser.add_argument('--save',type=str,default=r'D:\desk\defect_dataset\JASON/instances_test2017.json',help='config file')

2、 VOC格式转YOLO格式

"""

VOC转YOLO格式

"""
import xml.etree.ElementTree as ET
import os, cv2
import numpy as np
from os import listdir
from os.path import join

#需修改，添加数据集的类别
classes = []

def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)


def convert_annotation(xmlpath, xmlname):
    with open(xmlpath, "r", encoding='utf-8') as in_file:
        txtname = xmlname[:-4] + '.txt'
        txtfile = os.path.join(txtpath, txtname)
        tree = ET.parse(in_file)
        root = tree.getroot()
        filename = root.find('filename')
        img = cv2.imdecode(np.fromfile('{}/{}.{}'.format(imgpath, xmlname[:-4], postfix), np.uint8), cv2.IMREAD_COLOR)
        h, w = img.shape[:2]
        res = []
        for obj in root.iter('object'):
            cls = obj.find('name').text
            if cls not in classes:
                classes.append(cls)
            cls_id = classes.index(cls)
            xmlbox = obj.find('bndbox')
            b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
                 float(xmlbox.find('ymax').text))
            bb = convert((w, h), b)
            res.append(str(cls_id) + " " + " ".join([str(a) for a in bb]))
        if len(res) != 0:
            with open(txtfile, 'w+') as f:
                f.write('\n'.join(res))


if __name__ == "__main__":
#确保图片后缀为统一的jpg格式
    postfix = 'jpg'

#需修改，改为自己的图片所在位置
    imgpath = r'D:\desk\defect_dataset\IMG'

#需修改，改为自己的VOC标签格式所在位置
    xmlpath = r'D:\desk\defect_dataset\VOC'

#需修改，改为自己的想保存YOLO标签格式所在位置
    txtpath = r'D:\desk\defect_dataset\TXT'
    
    if not os.path.exists(txtpath):
        os.makedirs(txtpath, exist_ok=True)
    
    list = os.listdir(xmlpath)
    error_file_list = []
    for i in range(0, len(list)):
        try:
            path = os.path.join(xmlpath, list[i])
            if ('.xml' in path) or ('.XML' in path):
                convert_annotation(path, list[i])
                print(f'file {list[i]} convert success.')
            else:
                print(f'file {list[i]} is not xml format.')
        except Exception as e:
            print(f'file {list[i]} convert error.')
            print(f'error message:\n{e}')
            error_file_list.append(list[i])
    print(f'this file convert failure\n{error_file_list}')
    print(f'Dataset Classes:{classes}')

 上述代码中仅需要修改以下部分，再运行即可完成VOC格式转换为YOLO格式 

7行
# 需修改，添加数据集的类别
classes = []

54行
# 需修改，改为自己的图片所在位置
imgpath = r'D:\desk\defect_dataset\IMG'

57行
# 需修改，改为自己的VOC标签格式所在位置
xmlpath = r'D:\desk\defect_dataset\VOC'

60行
# 需修改，改为自己的想保存YOLO标签格式所在位置
txtpath = r'D:\desk\defect_dataset\TXT'

 3、YOLO格式转VOC格式

"""

YOLO转VOC格式

"""

from xml.dom.minidom import Document
import os
import cv2

def makexml(picPath, txtPath, xmlPath):  # txt所在文件夹路径，xml文件保存路径，图片所在文件夹路径

#需修改，数据集类别，注意一一对应
    dic = {'0': "crazing",
           '1': "patches",
           '2' :'inclusion',
           '3': "pitted_surface",
           '4': "rolled-in_scale",
           '5': "scratches",
           }

    files = os.listdir(txtPath)
    for i, name in enumerate(files):
        xmlBuilder = Document()
        annotation = xmlBuilder.createElement("annotation")  # 创建annotation标签
        xmlBuilder.appendChild(annotation)
        txtFile = open(txtPath + name)
        txtList = txtFile.readlines()
        img = cv2.imread(picPath + name[0:-4] + ".jpg")
        Pheight, Pwidth, Pdepth = img.shape

        folder = xmlBuilder.createElement("folder")  # folder标签
        foldercontent = xmlBuilder.createTextNode("driving_annotation_dataset")
        folder.appendChild(foldercontent)
        annotation.appendChild(folder)  # folder标签结束

        filename = xmlBuilder.createElement("filename")  # filename标签
        filenamecontent = xmlBuilder.createTextNode(name[0:-4] + ".jpg")
        filename.appendChild(filenamecontent)
        annotation.appendChild(filename)  # filename标签结束

        size = xmlBuilder.createElement("size")  # size标签
        width = xmlBuilder.createElement("width")  # size子标签width
        widthcontent = xmlBuilder.createTextNode(str(Pwidth))
        width.appendChild(widthcontent)
        size.appendChild(width)  # size子标签width结束

        height = xmlBuilder.createElement("height")  # size子标签height
        heightcontent = xmlBuilder.createTextNode(str(Pheight))
        height.appendChild(heightcontent)
        size.appendChild(height)  # size子标签height结束

        depth = xmlBuilder.createElement("depth")  # size子标签depth
        depthcontent = xmlBuilder.createTextNode(str(Pdepth))
        depth.appendChild(depthcontent)
        size.appendChild(depth)  # size子标签depth结束

        annotation.appendChild(size)  # size标签结束

        for j in txtList:
            oneline = j.strip().split(" ")
            object = xmlBuilder.createElement("object")  # object 标签
            picname = xmlBuilder.createElement("name")  # name标签
            namecontent = xmlBuilder.createTextNode(dic[oneline[0]])
            picname.appendChild(namecontent)
            object.appendChild(picname)  # name标签结束

            pose = xmlBuilder.createElement("pose")  # pose标签
            posecontent = xmlBuilder.createTextNode("Unspecified")
            pose.appendChild(posecontent)
            object.appendChild(pose)  # pose标签结束

            truncated = xmlBuilder.createElement("truncated")  # truncated标签
            truncatedContent = xmlBuilder.createTextNode("0")
            truncated.appendChild(truncatedContent)
            object.appendChild(truncated)  # truncated标签结束

            difficult = xmlBuilder.createElement("difficult")  # difficult标签
            difficultcontent = xmlBuilder.createTextNode("0")
            difficult.appendChild(difficultcontent)
            object.appendChild(difficult)  # difficult标签结束

            bndbox = xmlBuilder.createElement("bndbox")  # bndbox标签
            xmin = xmlBuilder.createElement("xmin")  # xmin标签
            mathData = int(((float(oneline[1])) * Pwidth + 1) - (float(oneline[3])) * 0.5 * Pwidth)
            xminContent = xmlBuilder.createTextNode(str(mathData))
            xmin.appendChild(xminContent)
            bndbox.appendChild(xmin)  # xmin标签结束

            ymin = xmlBuilder.createElement("ymin")  # ymin标签
            mathData = int(((float(oneline[2])) * Pheight + 1) - (float(oneline[4])) * 0.5 * Pheight)
            yminContent = xmlBuilder.createTextNode(str(mathData))
            ymin.appendChild(yminContent)
            bndbox.appendChild(ymin)  # ymin标签结束

            xmax = xmlBuilder.createElement("xmax")  # xmax标签
            mathData = int(((float(oneline[1])) * Pwidth + 1) + (float(oneline[3])) * 0.5 * Pwidth)
            xmaxContent = xmlBuilder.createTextNode(str(mathData))
            xmax.appendChild(xmaxContent)
            bndbox.appendChild(xmax)  # xmax标签结束

            ymax = xmlBuilder.createElement("ymax")  # ymax标签
            mathData = int(((float(oneline[2])) * Pheight + 1) + (float(oneline[4])) * 0.5 * Pheight)
            ymaxContent = xmlBuilder.createTextNode(str(mathData))
            ymax.appendChild(ymaxContent)
            bndbox.appendChild(ymax)  # ymax标签结束

            object.appendChild(bndbox)  # bndbox标签结束

            annotation.appendChild(object)  # object标签结束

        f = open(xmlPath + name[0:-4] + ".xml", 'w')
        xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
        f.close()


if __name__ == "__main__":

	# 需修改，图片所在文件夹路径
    picPath = r"D:\desk\defect_dataset\IMG/"

	# 需修改，YOLO标签所在文件夹路径
    txtPath = r"D:\desk\defect_dataset\TXT/"

	# 需修改，VOC文件保存路径
    xmlPath = r"D:\desk\defect_dataset\VOC/"

    makexml(picPath, txtPath, xmlPath)

  上述代码中仅需要修改以下部分，再运行即可完成YOLO格式转换为VOC格式 

11行
#需修改，数据集类别，注意一一对应
    dic = {'0': "crazing",
           '1': "patches",
           '2' :'inclusion',
           '3': "pitted_surface",
           '4': "rolled-in_scale",
           '5': "scratches",
           }

117行
# 需修改，图片所在文件夹路径
   picPath = r"D:\desk\defect_dataset\IMG/"

120行
# 需修改，YOLO标签所在文件夹路径
   txtPath = r"D:\desk\defect_dataset\TXT/"

123行
# 需修改，VOC文件保存路径
   xmlPath = r"D:\desk\defect_dataset\VOC/"

4、JSON格式转YOLO格式 

# COCO 格式的数据集转化为 YOLO 格式的数据集
# --json_path 输入的json文件路径
# --save_path 保存的文件夹名字，默认为当前目录下的labels。

import os
import json
from tqdm import tqdm
import argparse

parser = argparse.ArgumentParser()
# 需修改，这里替换自己的json文件位置
parser.add_argument('--json_path',
                    default=r'D:\desk\asssssssssssssss\try\json\instances_val2017.json', type=str,
                    help="input: coco format(json)")

# 需修改，这里输出的txt文件保存位置
parser.add_argument('--save_path', default=r'D:\desk\asssssssssssssss\try\txt', type=str,
                    help="specify where to save the output dir of labels")

# 需修改，这里设置json标签对应的图片文件位置
parser.add_argument('--img_path', default=r'D:\desk\asssssssssssssss\try\img', type=str,
                    help="all img path")

arg = parser.parse_args()


def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = box[0] + box[2] / 2.0
    y = box[1] + box[3] / 2.0
    w = box[2]
    h = box[3]
    # round函数确定(xmin, ymin, xmax, ymax)的小数位数
    x = round(x * dw, 6)
    w = round(w * dw, 6)
    y = round(y * dh, 6)
    h = round(h * dh, 6)
    return (x, y, w, h)


if __name__ == '__main__':
    json_file = arg.json_path  # COCO Object Instance 类型的标注
    ana_txt_save_path = arg.save_path  # 保存的路径

    data = json.load(open(json_file, 'r'))
    if not os.path.exists(ana_txt_save_path):
        os.makedirs(ana_txt_save_path)

    id_map = {}  # coco数据集的id不连续！重新映射一下再输出！
    with open(os.path.join(ana_txt_save_path, 'classes.txt'), 'w') as f:
        # 写入classes.txt
        for i, category in enumerate(data['categories']):
            f.write(f"{category['name']}\n")
            id_map[category['id']] = i
    # print(id_map)
    # 这里需要根据自己的需要，更改写入图像相对路径的文件位置。
    list_file = open(os.path.join(ana_txt_save_path, 'train2017.txt'), 'w')
    for img in tqdm(data['images']):
        filename = img["file_name"]
        img_width = img["width"]
        img_height = img["height"]
        img_id = img["id"]
        head, tail = os.path.splitext(filename)
        ana_txt_name = head + ".txt"  # 对应的txt名字，与jpg一致
        f_txt = open(os.path.join(ana_txt_save_path, ana_txt_name), 'w')
        for ann in data['annotations']:
            if ann['image_id'] == img_id:
                box = convert((img_width, img_height), ann["bbox"])
                f_txt.write("%s %s %s %s %s\n" % (id_map[ann["category_id"]], box[0], box[1], box[2], box[3]))
        f_txt.close()
        list_file.write(os.path.join(arg.img_path,r'%s.jpg\n') % (head))#修改

    list_file.close()

 上述代码中仅需要修改以下部分，再运行即可完成JSON格式转换为YOLO格式  

11行
# 需修改，这里替换自己的json文件位置
parser.add_argument('--json_path',
                    default=r'D:\desk\asssssssssssssss\try\json\instances_val2017.json', type=str,
                    help="input: coco format(json)")

16行
# 需修改，这里输出的txt文件保存位置
parser.add_argument('--save_path', default=r'D:\desk\asssssssssssssss\try\txt', type=str,
                    help="specify where to save the output dir of labels")

20行
# 需修改，这里设置json标签对应的图片文件位置
parser.add_argument('--img_path', default=r'D:\desk\asssssssssssssss\try\img', type=str,
                    help="all img path")

---

代码仅用于本人学习使用