深度学习数据集不同格式的脚本转换

目录

json→txt

txt→xml

xml→txt

---

来源：交流群

json→txt

import json
import os

name2id = {'person':0,'bag':1,'div':2}
               
def convert(img_size, box):
    dw = 1./(img_size[0])
    dh = 1./(img_size[1])
    x = (box[0] + box[2])/2.0 - 1
    y = (box[1] + box[3])/2.0 - 1
    w = box[2] - box[0]
    h = box[3] - box[1]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)
 
 
def decode_json(json_floder_path,json_name):
 #转换好的输出路径
    txt_name = 'data\\custom\\labels\\' + json_name[0:-5] + '.txt'
    txt_file = open(txt_name, 'w')
 
    json_path = os.path.join(json_floder_path, json_name)
    data = json.load(open(json_path, 'r', encoding='gb2312'))
 
    img_w = data['imageWidth']
    img_h = data['imageHeight']
 
    for i in data['shapes']:
        
        label_name = i['label']
        if (i['shape_type'] == 'rectangle'):
 
            x1 = int(i['points'][0][0])
            y1 = int(i['points'][0][1])
            x2 = int(i['points'][1][0])
            y2 = int(i['points'][1][1])
 
            bb = (x1,y1,x2,y2)
            bbox = convert((img_w,img_h),bb)
            txt_file.write(str(name2id[label_name]) + " " + " ".join([str(a) for a in bbox]) + '\n')
    
if __name__ == "__main__":
    #labelme生成标签的路径
    json_floder_path = 'E:\\Information\\Laboratory\\labelImg\\label\\'
    json_names = os.listdir(json_floder_path)
    for json_name in json_names:
        decode_json(json_floder_path,json_name)

txt→xml

# .txt-->.xml
# ! /usr/bin/python
# -*- coding:UTF-8 -*-
import os
import cv2


def txt_to_xml(txt_path, img_path, xml_path):
    # 1.字典对标签中的类别进行转换
    dict = {'0': "car",
            '1': "truck",
            '2': "bus",
            '3': "person",
            '4': "fire",
            '5': "smoke",
            '6': "cone",
            '7': "div",
            '8': "suit",
            '9': "box",
            '10': "moto",
            }
    # 2.找到txt标签文件夹
    files = os.listdir(txt_path)
    # 用于存储 "老图"
    pre_img_name = ''
    # 3.遍历文件夹
    for i, name in enumerate(files):
        # 许多人文件夹里有该文件，默认的也删不掉，那就直接pass
        if name == "desktop.ini":
            continue
        print(name)
        # 4.打开txt
        txtFile = open(txt_path + name)
        # 读取所有内容
        txtList = txtFile.readlines()
        # 读取图片名称
        img_name = name.split(".")[0]
        pic = cv2.imread(img_path + img_name + ".jpg")
        # 获取图像大小信息
        Pheight, Pwidth, Pdepth = pic.shape
        # 5.遍历txt文件中每行内容
        for row in txtList:
            # 按' '分割txt的一行的内容
            oneline = row.strip().split(" ")
            # 遇到的是一张新图片
            if img_name != pre_img_name:
                # 6.新建xml文件
                xml_file = open((xml_path + img_name + '.xml'), 'w')
                xml_file.write('<annotation>\n')
                xml_file.write('    <folder>VOC2007</folder>\n')
                xml_file.write('    <filename>' + img_name + '.jpg' + '</filename>\n')
                xml_file.write('<source>\n')
                xml_file.write('<database>orgaquant</database>\n')
                xml_file.write('<annotation>organoids</annotation>\n')
                xml_file.write('</source>\n')
                xml_file.write('    <size>\n')
                xml_file.write('        <width>' + str(Pwidth) + '</width>\n')
                xml_file.write('        <height>' + str(Pheight) + '</height>\n')
                xml_file.write('        <depth>' + str(Pdepth) + '</depth>\n')
                xml_file.write('    </size>\n')
                xml_file.write('    <object>\n')
                xml_file.write('<name>' + dict[oneline[0]] + '</name>\n')
                xml_file.write('        <bndbox>\n')
                xml_file.write('            <xmin>' + str(
                    int(((float(oneline[1])) * Pwidth + 1) - (float(oneline[3])) * 0.5 * Pwidth)) + '</xmin>\n')
                xml_file.write('            <ymin>' + str(
                    int(((float(oneline[2])) * Pheight + 1) - (float(oneline[4])) * 0.5 * Pheight)) + '</ymin>\n')
                xml_file.write('            <xmax>' + str(
                    int(((float(oneline[1])) * Pwidth + 1) + (float(oneline[3])) * 0.5 * Pwidth)) + '</xmax>\n')
                xml_file.write('            <ymax>' + str(
                    int(((float(oneline[2])) * Pheight + 1) + (float(oneline[4])) * 0.5 * Pheight)) + '</ymax>\n')
                xml_file.write('        </bndbox>\n')
                xml_file.write('    </object>\n')
                xml_file.close()
                pre_img_name = img_name  # 将其设为"老"图
            else:  # 不是新图而是"老图"
                # 7.同一张图片，只需要追加写入object
                xml_file = open((xml_path + img_name + '.xml'), 'a')
                xml_file.write('    <object>\n')
                xml_file.write('<name>' + dict[oneline[0]] + '</name>\n')
                '''  按需添加这里和上面
                xml_file.write('        <pose>Unspecified</pose>\n')
                xml_file.write('        <truncated>0</truncated>\n')
                xml_file.write('        <difficult>0</difficult>\n')
                '''
                xml_file.write('        <bndbox>\n')
                xml_file.write('            <xmin>' + str(
                    int(((float(oneline[1])) * Pwidth + 1) - (float(oneline[3])) * 0.5 * Pwidth)) + '</xmin>\n')
                xml_file.write('            <ymin>' + str(
                    int(((float(oneline[2])) * Pheight + 1) - (float(oneline[4])) * 0.5 * Pheight)) + '</ymin>\n')
                xml_file.write('            <xmax>' + str(
                    int(((float(oneline[1])) * Pwidth + 1) + (float(oneline[3])) * 0.5 * Pwidth)) + '</xmax>\n')
                xml_file.write('            <ymax>' + str(
                    int(((float(oneline[2])) * Pheight + 1) + (float(oneline[4])) * 0.5 * Pheight)) + '</ymax>\n')
                xml_file.write('        </bndbox>\n')
                xml_file.write('    </object>\n')
                xml_file.close()

        # 8.读完txt文件最后写入</annotation>
        xml_file1 = open((xml_path + pre_img_name + '.xml'), 'a')
        xml_file1.write('</annotation>')
        xml_file1.close()
    print("Done !")


# 修改成自己的文件夹 注意文件夹最后要加上/
txt_to_xml("E:/Program/PyCharm/labelImg/labels/txt/", "E:/Program/PyCharm/labelImg/images/",
           "E:/Program/PyCharm/labelImg/labels/xml/")

xml→txt

import os
import xml.etree.ElementTree as ET


# xml文件存放目录（不要以\结尾）
input_dir = r'E:\Program\PyCharm\labelImg\labels\xml'

# 输出txt文件目录（不要以\结尾）
out_dir = r'E:\Program\PyCharm\labelImg\labels\txt'

class_list = []


# 获取目录所有xml文件
def file_name(input_dir):
    F = []
    for root, dirs, files in os.walk(input_dir):

        for file in files:
            # print file.decode('gbk')    #文件名中有中文字符时转码
            if os.path.splitext(file)[1] == '.xml':
                t = os.path.splitext(file)[0]
                F.append(t)  # 将所有的文件名添加到L列表中
    return F  # 返回L列表


# 获取所有分类
def get_class(filelist):
    for i in filelist:
        f_dir = input_dir + "\\" + i + ".xml"
        in_file = open(f_dir, encoding='UTF-8')
        filetree = ET.parse(in_file)
        in_file.close()
        root = filetree.getroot()
        for obj in root.iter('object'):
            difficult = obj.find('difficult').text
            cls = obj.find('name').text
            if cls not in class_list or int(difficult) == 1:
                class_list.append(cls)


def ConverCoordinate(imgshape, bbox):
    # 将xml像素坐标转换为txt归一化后的坐标
    xmin, xmax, ymin, ymax = bbox
    width = imgshape[0]
    height = imgshape[1]
    dw = 1. / width
    dh = 1. / height
    x = (xmin + xmax) / 2.0
    y = (ymin + ymax) / 2.0
    w = xmax - xmin
    h = ymax - ymin

    # 归一化
    x = x * dw
    y = y * dh
    w = w * dw
    h = h * dh

    return x, y, w, h


def readxml(i):
    f_dir = input_dir + "\\" + i + ".xml"

    txtresult = ''

    outfile = open(f_dir, encoding='UTF-8')
    filetree = ET.parse(outfile)
    outfile.close()
    root = filetree.getroot()

    # 获取图片大小
    size = root.find('size')
    width = int(size.find('width').text)
    height = int(size.find('height').text)
    imgshape = (width, height)

    # 转化为yolov5的格式
    for obj in root.findall('object'):
        # 获取类别名
        obj_name = obj.find('name').text

        obj_id = class_list.index(obj_name)
        # 获取每个obj的bbox框的左上和右下坐标
        bbox = obj.find('bndbox')
        xmin = float(bbox.find('xmin').text)
        xmax = float(bbox.find('xmax').text)
        ymin = float(bbox.find('ymin').text)
        ymax = float(bbox.find('ymax').text)
        bbox_coor = (xmin, xmax, ymin, ymax)

        x, y, w, h = ConverCoordinate(imgshape, bbox_coor)
        txt = '{} {} {} {} {}\n'.format(obj_id, x, y, w, h)
        txtresult = txtresult + txt

    # print(txtresult)
    f = open(out_dir + "\\" + i + ".txt", 'a')
    f.write(txtresult)
    f.close()


# 获取文件夹下的所有文件
filelist = file_name(input_dir)

# 获取所有分类
get_class(filelist)

# 打印class
print(class_list)

# xml转txt
for i in filelist:
    readxml(i)

# 在out_dir下生成一个class文件
f = open(out_dir + "\\classes.txt", 'a')
classresult = ''
for i in class_list:
    classresult = classresult + i + "\n"
f.write(classresult)
f.close()