JSON2YOLO

import json
import os
from collections import Counter
import numpy as np

file = r'D:\BaiduNetdiskDownload\dataset_v2\json_dataset'
def read_json(file,cates):
    # print(file)
    name = file.split('\\')[-1].split('.')[0]
    with open(file,'r')as f:
        a = json.load(f)
    uis = a['ui_components']
    cate = []
    bboxes = []
    for ui in uis:
        cate.append(ui['cls'])
        bboxes.append(ui['bounds'])

    bboxes = np.array(bboxes,dtype=float)
    bboxes[:,:4:2] = bboxes[:,:4:2]/1440.
    bboxes[:, 1:4:2] = bboxes[:, 1:4:2] / 2560.
    bboxes[:,2:] = bboxes[:,2:]-bboxes[:,:2]
    bboxes[:,:2] = bboxes[:,:2] + bboxes[:,2:]/2.
    with open(r'D:\BaiduNetdiskDownload\dataset_v2\txt\%s.txt'%name,'w+')as f:
        idx = -1
        for c,b in zip(cate,bboxes):
            if c not in cates:
                continue
            idx = cates.index(c)
            f.write('%d'%idx)
            for b_ in b:
                f.write(' %.5f'%b_)
            f.write('\n')
    if idx == -1:
        os.remove(r'D:\BaiduNetdiskDownload\dataset_v2\image_dataset'+'\\'+name+'.jpg')
        if os.path.exists(r'D:\BaiduNetdiskDownload\dataset_v2\txt\%s.txt'%name):
            os.remove(r'D:\BaiduNetdiskDownload\dataset_v2\txt\%s.txt'%name)
    return cate


if __name__ == '__main__':
    cates = ['TEXT', 'PICTOGRAM', 'BUTTON', 'IMAGE', 'TEXT_INPUT', 'CHECK_BOX', 'PAGER_INDICATOR', 'SWITCH', 'SLIDER', 'RADIO_BUTTON', 'PROGRESS_BAR', 'SPINNER']
    for i in os.listdir(file):
        cates.extend(read_json(file+'\\'+i,cates))
        # break
    print(Counter(cates))
    # with open('new_classes.txt','w+')as f:
    #     for c in cates:
    #         f.write(c+'\n')

YOLO2VOC

import os
import xml.etree.ElementTree as ET
from xml.dom.minidom import Document
import cv2
import multiprocessing
from tqdm import tqdm
'''
import xml
xml.dom.minidom.Document().writexml()
def writexml(self,
             writer: Any,
             indent: str = "",
             addindent: str = "",
             newl: str = "",
             encoding: Any = None) -> None
'''

class YOLO2VOCConvert:
    def __init__(self, txts_path, xmls_path, imgs_path):
        self.txts_path = txts_path   # 标注的yolo格式标签文件路径
        self.xmls_path = xmls_path   # 转化为voc格式标签之后保存路径
        self.imgs_path = imgs_path   # 读取读片的路径个图片名字，存储到xml标签文件中
        self.classes = ['granulocyte', 'mitotic figure', 'tumor cell', 'other/ambigous cells',
                        'binucleated cell', 'multinukleated cell', 'Mitotic figure lookalike']

    # 从所有的txt文件中提取出所有的类别， yolo格式的标签格式类别为数字 0,1,...
    # writer为True时，把提取的类别保存到'./Annotations/classes.txt'文件中
    def search_all_classes(self, writer=False):
        # 读取每一个txt标签文件，取出每个目标的标注信息
        all_names = set()
        txts = os.listdir(self.txts_path)
        # 使用列表生成式过滤出只有后缀名为txt的标签文件
        txts = [txt for txt in txts if txt.split('.')[-1] == 'txt']
        print(len(txts), txts)
        # 11 ['0002030.txt', '0002031.txt', ... '0002039.txt', '0002040.txt']
        for txt in txts:
            txt_file = os.path.join(self.txts_path, txt)
            with open(txt_file, 'r') as f:
                objects = f.readlines()
                for object in objects:
                    object = object.strip().split(' ')
                    print(object)  # ['2', '0.506667', '0.553333', '0.490667', '0.658667']
                    all_names.add(int(object[0]))
            # print(objects)  # ['2 0.506667 0.553333 0.490667 0.658667\n', '0 0.496000 0.285333 0.133333 0.096000\n', '8 0.501333 0.412000 0.074667 0.237333\n']

        print("所有的类别标签：", all_names, "共标注数据集：%d张" % len(txts))
        return list(all_names)

    def yolo2voc(self):
        # 创建一个保存xml标签文件的文件夹
        if not os.path.exists(self.xmls_path):
            os.mkdir(self.xmls_path)

        # 把上面的两个循环改写成为一个循环：
        imgs = os.listdir(self.imgs_path)
        txts = os.listdir(self.txts_path)
        txts = [txt for txt in txts if not txt.split('.')[0] == "classes"]  # 过滤掉classes.txt文件
        print(txts)

        # 注意，这里保持图片的数量和标签txt文件数量相等，且要保证名字是一一对应的   (后面改进，通过判断txt文件名是否在imgs中即可)
        if len(imgs) == len(txts):   # 注意：./Annotation_txt 不要把classes.txt文件放进去
            map_imgs_txts = [(img, txt) for img, txt in zip(imgs, txts)]
            txts = [txt for txt in txts if txt.split('.')[-1] == 'txt']
            print(len(txts), txts)
            for img_name, txt_name in map_imgs_txts:
                # 读取图片的尺度信息
                print("读取图片：", img_name)
                img = cv2.imread(os.path.join(self.imgs_path, img_name))
                height_img, width_img, depth_img = img.shape
                print(height_img, width_img, depth_img)   # h 就是多少行（对应图片的高度）， w就是多少列（对应图片的宽度）

                # 获取标注文件txt中的标注信息
                all_objects = []
                txt_file = os.path.join(self.txts_path, txt_name)
                with open(txt_file, 'r') as f:
                    objects = f.readlines()
                    for object in objects:
                        object = object.strip().split(' ')
                        all_objects.append(object)
                        print(object)  # ['2', '0.506667', '0.553333', '0.490667', '0.658667']

                # 创建xml标签文件中的标签
                xmlBuilder = Document()
                # 创建annotation标签，也是根标签
                annotation = xmlBuilder.createElement("annotation")

                # 给标签annotation添加一个子标签
                xmlBuilder.appendChild(annotation)

                # 创建子标签folder
                folder = xmlBuilder.createElement("folder")
                # 给子标签folder中存入内容，folder标签中的内容是存放图片的文件夹，例如：JPEGImages
                folderContent = xmlBuilder.createTextNode(self.imgs_path.split('/')[-1])  # 标签内存
                folder.appendChild(folderContent)  # 把内容存入标签
                annotation.appendChild(folder)   # 把存好内容的folder标签放到 annotation根标签下

                # 创建子标签filename
                filename = xmlBuilder.createElement("filename")
                # 给子标签filename中存入内容，filename标签中的内容是图片的名字，例如：000250.jpg
                filenameContent = xmlBuilder.createTextNode(txt_name.split('.')[0] + '.jpg')  # 标签内容
                filename.appendChild(filenameContent)
                annotation.appendChild(filename)

                # 把图片的shape存入xml标签中
                size = xmlBuilder.createElement("size")
                # 给size标签创建子标签width
                width = xmlBuilder.createElement("width")  # size子标签width
                widthContent = xmlBuilder.createTextNode(str(width_img))
                width.appendChild(widthContent)
                size.appendChild(width)   # 把width添加为size的子标签
                # 给size标签创建子标签height
                height = xmlBuilder.createElement("height")  # size子标签height
                heightContent = xmlBuilder.createTextNode(str(height_img))  # xml标签中存入的内容都是字符串
                height.appendChild(heightContent)
                size.appendChild(height)  # 把width添加为size的子标签
                # 给size标签创建子标签depth
                depth = xmlBuilder.createElement("depth")  # size子标签width
                depthContent = xmlBuilder.createTextNode(str(depth_img))
                depth.appendChild(depthContent)
                size.appendChild(depth)  # 把width添加为size的子标签
                annotation.appendChild(size)   # 把size添加为annotation的子标签

                # 每一个object中存储的都是['2', '0.506667', '0.553333', '0.490667', '0.658667']一个标注目标
                for object_info in all_objects:
                    # 开始创建标注目标的label信息的标签
                    object = xmlBuilder.createElement("object")  # 创建object标签
                    # 创建label类别标签
                    # 创建name标签
                    imgName = xmlBuilder.createElement("name")  # 创建name标签
                    imgNameContent = xmlBuilder.createTextNode(self.classes[int(object_info[0])])
                    imgName.appendChild(imgNameContent)
                    object.appendChild(imgName)  # 把name添加为object的子标签

                    # 创建pose标签
                    pose = xmlBuilder.createElement("pose")
                    poseContent = xmlBuilder.createTextNode("Unspecified")
                    pose.appendChild(poseContent)
                    object.appendChild(pose)  # 把pose添加为object的标签

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

                    # 创建difficult标签
                    difficult = xmlBuilder.createElement("difficult")
                    difficultContent = xmlBuilder.createTextNode("0")
                    difficult.appendChild(difficultContent)
                    object.appendChild(difficult)

                    # 先转换一下坐标
                    # (objx_center, objy_center, obj_width, obj_height)->(xmin，ymin, xmax,ymax)
                    x_center = float(object_info[1])*width_img + 1
                    y_center = float(object_info[2])*height_img + 1
                    xminVal = int(x_center - 0.5*float(object_info[3])*width_img)   # object_info列表中的元素都是字符串类型
                    yminVal = int(y_center - 0.5*float(object_info[4])*height_img)
                    xmaxVal = int(x_center + 0.5*float(object_info[3])*width_img)
                    ymaxVal = int(y_center + 0.5*float(object_info[4])*height_img)



                    # 创建bndbox标签(三级标签)
                    bndbox = xmlBuilder.createElement("bndbox")
                    # 在bndbox标签下再创建四个子标签(xmin，ymin, xmax,ymax) 即标注物体的坐标和宽高信息
                    # 在voc格式中，标注信息：左上角坐标（xmin, ymin） （xmax, ymax）右下角坐标
                    # 1、创建xmin标签
                    xmin = xmlBuilder.createElement("xmin")  # 创建xmin标签（四级标签）
                    xminContent = xmlBuilder.createTextNode(str(xminVal))
                    xmin.appendChild(xminContent)
                    bndbox.appendChild(xmin)
                    # 2、创建ymin标签
                    ymin = xmlBuilder.createElement("ymin")  # 创建ymin标签（四级标签）
                    yminContent = xmlBuilder.createTextNode(str(yminVal))
                    ymin.appendChild(yminContent)
                    bndbox.appendChild(ymin)
                    # 3、创建xmax标签
                    xmax = xmlBuilder.createElement("xmax")  # 创建xmax标签（四级标签）
                    xmaxContent = xmlBuilder.createTextNode(str(xmaxVal))
                    xmax.appendChild(xmaxContent)
                    bndbox.appendChild(xmax)
                    # 4、创建ymax标签
                    ymax = xmlBuilder.createElement("ymax")  # 创建ymax标签（四级标签）
                    ymaxContent = xmlBuilder.createTextNode(str(ymaxVal))
                    ymax.appendChild(ymaxContent)
                    bndbox.appendChild(ymax)

                    object.appendChild(bndbox)
                    annotation.appendChild(object)  # 把object添加为annotation的子标签
                f = open(os.path.join(self.xmls_path, txt_name.split('.')[0]+'.xml'), 'w')
                xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
                f.close()




import matplotlib.pyplot as plt
def yolo2voc(img_name,txt_name,xmls_path,imgs_path,txts_path,classes):
    print("读取图片：", img_name)
    img = cv2.imread(os.path.join(imgs_path, img_name))
    height_img, width_img, depth_img = img.shape
    # height_img, width_img, depth_img = 640,640,3
    # print(height_img, width_img, depth_img)   # h 就是多少行（对应图片的高度）， w就是多少列（对应图片的宽度）

    # 获取标注文件txt中的标注信息
    all_objects = []
    txt_file = os.path.join(txts_path, txt_name)
    with open(txt_file, 'r') as f:
        objects = f.readlines()
        for object in objects:
            object = object.strip().split(' ')
            all_objects.append(object)
            print(object)  # ['2', '0.506667', '0.553333', '0.490667', '0.658667']

    # 创建xml标签文件中的标签
    xmlBuilder = Document()
    # 创建annotation标签，也是根标签
    annotation = xmlBuilder.createElement("annotation")

    # 给标签annotation添加一个子标签
    xmlBuilder.appendChild(annotation)

    # 创建子标签folder
    folder = xmlBuilder.createElement("folder")
    # 给子标签folder中存入内容，folder标签中的内容是存放图片的文件夹，例如：JPEGImages
    folderContent = xmlBuilder.createTextNode(imgs_path.split('/')[-1])  # 标签内存
    folder.appendChild(folderContent)  # 把内容存入标签
    annotation.appendChild(folder)   # 把存好内容的folder标签放到 annotation根标签下

    # 创建子标签filename
    filename = xmlBuilder.createElement("filename")
    # 给子标签filename中存入内容，filename标签中的内容是图片的名字，例如：000250.jpg
    filenameContent = xmlBuilder.createTextNode(txt_name.split('.')[0] + '.jpg')  # 标签内容
    filename.appendChild(filenameContent)
    annotation.appendChild(filename)

    # 把图片的shape存入xml标签中
    size = xmlBuilder.createElement("size")
    # 给size标签创建子标签width
    width = xmlBuilder.createElement("width")  # size子标签width
    widthContent = xmlBuilder.createTextNode(str(width_img))
    width.appendChild(widthContent)
    size.appendChild(width)   # 把width添加为size的子标签
    # 给size标签创建子标签height
    height = xmlBuilder.createElement("height")  # size子标签height
    heightContent = xmlBuilder.createTextNode(str(height_img))  # xml标签中存入的内容都是字符串
    height.appendChild(heightContent)
    size.appendChild(height)  # 把width添加为size的子标签
    # 给size标签创建子标签depth
    depth = xmlBuilder.createElement("depth")  # size子标签width
    depthContent = xmlBuilder.createTextNode(str(depth_img))
    depth.appendChild(depthContent)
    size.appendChild(depth)  # 把width添加为size的子标签
    annotation.appendChild(size)   # 把size添加为annotation的子标签

    # 每一个object中存储的都是['2', '0.506667', '0.553333', '0.490667', '0.658667']一个标注目标
    for object_info in all_objects:
        # 开始创建标注目标的label信息的标签
        object = xmlBuilder.createElement("object")  # 创建object标签
        # 创建label类别标签
        # 创建name标签
        imgName = xmlBuilder.createElement("name")  # 创建name标签
        imgNameContent = xmlBuilder.createTextNode(classes[int(object_info[0])])
        imgName.appendChild(imgNameContent)
        object.appendChild(imgName)  # 把name添加为object的子标签

        # 创建pose标签
        pose = xmlBuilder.createElement("pose")
        poseContent = xmlBuilder.createTextNode("Unspecified")
        pose.appendChild(poseContent)
        object.appendChild(pose)  # 把pose添加为object的标签

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

        # 创建difficult标签
        difficult = xmlBuilder.createElement("difficult")
        difficultContent = xmlBuilder.createTextNode("0")
        difficult.appendChild(difficultContent)
        object.appendChild(difficult)

        # 先转换一下坐标
        # (objx_center, objy_center, obj_width, obj_height)->(xmin，ymin, xmax,ymax)
        x_center = float(object_info[1])*width_img + 1
        y_center = float(object_info[2])*height_img + 1
        xminVal = int(x_center - 0.5*float(object_info[3])*width_img)   # object_info列表中的元素都是字符串类型
        yminVal = int(y_center - 0.5*float(object_info[4])*height_img)
        xmaxVal = int(x_center + 0.5*float(object_info[3])*width_img)
        ymaxVal = int(y_center + 0.5*float(object_info[4])*height_img)



        # 创建bndbox标签(三级标签)
        bndbox = xmlBuilder.createElement("bndbox")
        # 在bndbox标签下再创建四个子标签(xmin，ymin, xmax,ymax) 即标注物体的坐标和宽高信息
        # 在voc格式中，标注信息：左上角坐标（xmin, ymin） （xmax, ymax）右下角坐标
        # 1、创建xmin标签
        xmin = xmlBuilder.createElement("xmin")  # 创建xmin标签（四级标签）
        xminContent = xmlBuilder.createTextNode(str(xminVal))
        xmin.appendChild(xminContent)
        bndbox.appendChild(xmin)
        # 2、创建ymin标签
        ymin = xmlBuilder.createElement("ymin")  # 创建ymin标签（四级标签）
        yminContent = xmlBuilder.createTextNode(str(yminVal))
        ymin.appendChild(yminContent)
        bndbox.appendChild(ymin)
        # 3、创建xmax标签
        xmax = xmlBuilder.createElement("xmax")  # 创建xmax标签（四级标签）
        xmaxContent = xmlBuilder.createTextNode(str(xmaxVal))
        xmax.appendChild(xmaxContent)
        bndbox.appendChild(xmax)
        # 4、创建ymax标签
        ymax = xmlBuilder.createElement("ymax")  # 创建ymax标签（四级标签）
        ymaxContent = xmlBuilder.createTextNode(str(ymaxVal))
        ymax.appendChild(ymaxContent)
        bndbox.appendChild(ymax)

        object.appendChild(bndbox)
        annotation.appendChild(object)  # 把object添加为annotation的子标签
    f = open(os.path.join(xmls_path, txt_name.split('.')[0]+'.xml'), 'w')
    xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
    f.close()
def print_error(value):
    print("error: ", value)

if __name__ == '__main__':
    print('开始运行主线程')
    multiprocessing.freeze_support()
    multiprocessing.Process()
    pool = multiprocessing.Pool(multiprocessing.cpu_count())
    txts_path1 = r'D:\BaiduNetdiskDownload\dataset_v2\txt'
    xmls_path1 = r'D:\BaiduNetdiskDownload\dataset_v2\xml'
    imgs_path1 = r'D:\BaiduNetdiskDownload\dataset_v2\image_dataset'
    classes = ['TEXT', 'PICTOGRAM', 'BUTTON', 'IMAGE', 'TEXT_INPUT', 'CHECK_BOX', 'PAGER_INDICATOR', 'SWITCH', 'SLIDER', 'RADIO_BUTTON', 'PROGRESS_BAR', 'SPINNER']


    # with open('new_classes.txt', 'r') as f:
    #     classes = f.readlines()
    #     classes = [i.split('\n')[0] for i in classes]

    #
    if not os.path.exists(xmls_path1):
        os.mkdir(xmls_path1)

    # 把上面的两个循环改写成为一个循环：
    imgs = os.listdir(imgs_path1)
    txts = os.listdir(txts_path1)
    txts = [txt for txt in txts if not txt.split('.')[0] == "classes"]  # 过滤掉classes.txt文件
    print(txts)

    # 注意，这里保持图片的数量和标签txt文件数量相等，且要保证名字是一一对应的   (后面改进，通过判断txt文件名是否在imgs中即可)
    if len(imgs) == len(txts):   # 注意：./Annotation_txt 不要把classes.txt文件放进去
        map_imgs_txts = [(img, txt) for img, txt in zip(imgs, txts)]
        txts = [txt for txt in txts if txt.split('.')[-1] == 'txt']
        print(len(txts), txts)
        num_q = 0
        with tqdm(total=len(map_imgs_txts),desc='',postfix=dict,mininterval=0.3)as pbar:
            for img_name, txt_name in map_imgs_txts:
                num_q += 1
                pool.apply_async(func=yolo2voc, args=[img_name, txt_name, xmls_path1, imgs_path1, txts_path1, classes],
                                 callback=print_error)
                # pbar.set_postfix(**{'sample:',num_q})
                # pbar.set_postfix(**{'sample:',num_q})
                pbar.update(1)
            pool.close()
            pool.join()
            print('主线程运行结束')

COCO2YOLO（网上找的代码，找不到出处了）

# coco2voc.py

# pip install pycocotools
import os
import time
import json
import pandas as pd
from tqdm import tqdm
from pycocotools.coco import COCO
 
#json文件路径和用于存放xml文件的路径
anno = r'E:\BaiduNetdiskDownload\SODA-D\Annotations\train.json'
xml_dir = r'E:\BaiduNetdiskDownload\SODA-D\Annotations\xml'

coco = COCO(anno)  # 读文件
cats = coco.loadCats(coco.getCatIds())  # 这里loadCats就是coco提供的接口，获取类别
    
# Create anno dir
dttm = time.strftime("%Y%m%d%H%M%S", time.localtime())

def trans_id(category_id):
    names = []
    namesid = []
    for i in range(0, len(cats)):
        names.append(cats[i]['name'])
        namesid.append(cats[i]['id'])
    index = namesid.index(category_id)
    return index
    

def convert(anno,xml_dir): 

    with open(anno, 'r') as load_f:
        f = json.load(load_f)
    
    imgs = f['images']  #json文件的img_id和图片对应关系 imgs列表表示多少张图
    
    cat = f['categories']
    df_cate = pd.DataFrame(f['categories'])                     # json中的类别
    df_cate_sort = df_cate.sort_values(["id"], ascending=True)  # 按照类别id排序
    categories = list(df_cate_sort['name'])                     # 获取所有类别名称
    print('categories = ', categories)
    df_anno = pd.DataFrame(f['annotations'])                    # json中的annotation
    
    for i in tqdm(range(len(imgs))):  # 大循环是images所有图片,Tqdm是可扩展的Python进度条，可以在长循环中添加一个进度提示信息
        xml_content = []
        file_name = imgs[i]['file_name']    # 通过img_id找到图片的信息
        height = imgs[i]['height']
        img_id = imgs[i]['id']
        width = imgs[i]['width']
        
        version =['"1.0"','"utf-8"'] 
    
        # xml文件添加属性
        xml_content.append("<?xml version=" + version[0] +" "+ "encoding="+ version[1] + "?>")
        xml_content.append("<annotation>")
        xml_content.append("    <filename>" + file_name + "</filename>")
        xml_content.append("    <size>")
        xml_content.append("        <width>" + str(width) + "</width>")
        xml_content.append("        <height>" + str(height) + "</height>")
        xml_content.append("        <depth>"+ "3" + "</depth>")
        xml_content.append("    </size>")
    
        # 通过img_id找到annotations
        annos = df_anno[df_anno["image_id"].isin([img_id])]  # (2,8)表示一张图有两个框
    
        for index, row in annos.iterrows():  # 一张图的所有annotation信息
            bbox = row["bbox"]
            category_id = row["category_id"]
            cate_name = categories[trans_id(category_id)]
    
            # add new object
            xml_content.append("    <object>")
            xml_content.append("        <name>" + cate_name + "</name>")
            xml_content.append("        <truncated>0</truncated>")
            xml_content.append("        <difficult>0</difficult>")
            xml_content.append("        <bndbox>")
            xml_content.append("            <xmin>" + str(int(bbox[0])) + "</xmin>")
            xml_content.append("            <ymin>" + str(int(bbox[1])) + "</ymin>")
            xml_content.append("            <xmax>" + str(int(bbox[0] + bbox[2])) + "</xmax>")
            xml_content.append("            <ymax>" + str(int(bbox[1] + bbox[3])) + "</ymax>")
            xml_content.append("        </bndbox>")
            xml_content.append("    </object>")
        xml_content.append("</annotation>")
    
        x = xml_content
        xml_content = [x[i] for i in range(0, len(x)) if x[i] != "\n"]
        ### list存入文件
        #xml_path = os.path.join(xml_dir, file_name.replace('.xml', '.jpg'))
        xml_path = os.path.join(xml_dir, file_name.split('j')[0]+'xml')
        print(xml_path)
        with open(xml_path, 'w+', encoding="utf8") as f:
            f.write('\n'.join(xml_content))
        xml_content[:] = []

if __name__ == '__main__':
    convert(anno,xml_dir)