yolo系列不同模型训练的时候 数据集标注文件之间的相互转换

yolo系列不同模型训练的时候 数据集标注文件之间的相互转换

一 将标注精灵标注的json文件转换为yolov5训练所需的txt格式，需依次遍历每一个json

def json2txt():
    from tqdm import tqdm, trange

    ''' 标注精灵的json（x1,y1,x2,y2）文件转训练所用txt（x0,y0,w,h）'''
    
    name2307 = {'pedes': 0, 'car': 1, 'bus': 2, 'bigtru': 3, 'bike': 4, 'elec': 5, 'tricycle': 6, 'coni': 7, 'warm': 8,
               'polic': 1, 'tralight': 9, 'ambu': 10, 'fireen': 10,
              'pedes            ': 0, 'car ': 1, '  car': 1, ' car': 1, ' ca   r': 1, 'suv': 1, 'van': 1,
              'mpv': 1, 'pickup': 1, 'ar': 1, 'pedesd': 0, 'coach ': 2, 'car  ': 1,
              'suv ': 1, 'coach': 2,'trailer': 3, 'crane': 3, 'smatru': 3, 'tank': 3, 'escort': 10,
              'engine': 10, 'bull': 10, 'excava': 10, 'military': 10, 'elec ': 5, 'moto': 5, 'motopoli': 5}
    #name2307 = {#pedes: 0,#car: 1,#bus: 2,#truck: 3,#bike: 4,#elec: 5,#tricycle: 6,#coni: 7,#warm: 8,#tralight: 9,#special_vehicles: 10,}    

    # 如下参数需根据情况进行修改
    namell = name2307
    pathimg =    r'D:\yolov5train\datasTrain3_More\images\val'
    pathjson = r'E:\datasTrainALL\OrdinaryRoad00_outputs44285'
    despathtxt = r'D:\yolov5train\datasTrain3_More\labels\val'

    files = os.listdir(pathimg)
    print(len(files))
    # files = [x for x in files if x[-4:] == '.jpg']
    ic = 0
    ycfile = []
    # for f in files[:]:
    for i in tqdm(range(len(files)), desc='进度：'):
        f = files[i]
        ic = ic + 1
        # print(ic, ':  ', f)

        if (f[-4:] != '.jpg'):
            continue
        imgShape = cv2.imread(os.path.join(pathimg, f)).shape
        imgw, imgh = imgShape[1], imgShape[0]

        json_path_name = os.path.join(pathjson, f[:-4] + '.json')
        with open(json_path_name, 'r', encoding='utf-8') as rf:
            rf = json.load(rf)

            try:
                objs = rf['outputs']['object']
            except:
                ycfile.append(f)
                print(ycfile)
                # break
                continue
            boxs = []
            for o in objs:
                try:
                    id = o['name']
                    if id not in namell.keys():
                        continue
                    id = str(namell[id])
                    xmin = o['bndbox']['xmin']
                    ymin = o['bndbox']['ymin']
                    xmax = o['bndbox']['xmax']
                    ymax = o['bndbox']['ymax']
                    ymax = imgh if (ymax > imgh or (imgh - ymax<5)) else ymax
                    ymin = 0 if  ymin < 5 else ymin
                    xmax = imgw if (xmax > imgw or (imgw - xmax < 5)) else xmax
                    xmin = 0 if xmin < 5 else xmin
                    x = (xmin + xmax) / 2 / imgw
                    y = (ymin + ymax) / 2 / imgh
                    w = (xmax - xmin) / imgw
                    h = (ymax - ymin) / imgh
                    x = str(x) if len(str(x)) <= 7 else str(x)[:7]
                    y = str(y) if len(str(y)) <= 7 else str(y)[:7]
                    w = str(w) if len(str(w)) <= 7 else str(w)[:7]
                    h = str(h) if len(str(h)) <= 7 else str(h)[:7]
                    box = id + ' ' + x + ' ' + y + ' ' + w + ' ' + h + '\n'
                    boxs.append(box)
                except:
                    continue
            if boxs == []:
                continue
            boxs[-1] = boxs[-1].replace('\n', '')

        txt_path_name = os.path.join(despathtxt, f[:-4] + '.txt')
        with open(txt_path_name, 'w', encoding='utf-8') as wf:
            wf.writelines(boxs)

    print(ycfile)

二 将yolov5的txt格式转化为yolovX的xml，需依次遍历每一个txt文件。

ref :https://zhuanlan.zhihu.com/p/525950939

def txt2xml():
    """
    for YOLOX
    将yolov5的txt格式转化为yolovX的xml
    """
    # ref :https://zhuanlan.zhihu.com/p/525950939

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

    """
    此函数用于将yolov5格式txt标注文件转换为voc格式xml标注文件
    在自己的标注图片文件夹下建三个子文件夹
    """
    dic = {'0': "peses",  # 创建字典用来对类型进行转换
           '1': "car",  # 此处的字典要与自己的classes.txt文件中的类对应，且顺序要一致
           '2': "bus",
           '3': "truck",
           '4': "bike",
           '5': "elec",
           '6': "tricycle",
           '7': "coni",
           '8': "warm",
           '9': "tralight",
           '10': "special_vehicle"
           }
    picPath = "D:/yolov5train/datasTrain3_More/images/train/"  # 图片所在文件夹路径，后面的/一定要带上
    txtPath = "D:/yolov5train/datasTrain3_More/labels/train/"  # txt所在文件夹路径，后面的/一定要带上
    xmlPath = "D:/yolov5train/datasTrain3_More/annotations/train/"  # xml文件保存路径，后面的/一定要带上
    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()

        # break


def ImageSetsMain():
    """
    for YOLOX：将每一个数据文件名称保存在txt文件中
    """
    imgPath = r'D:\yolov5train\datasTrain3_More\images\train'
    xmlPath = r'D:\yolov5train\datasTrain3_More\labels\train'
    train_val_txtPath = r'D:\yolov5train\datasTrain3_More\ImageSets\Main\train.txt'

    imgs = os.listdir(imgPath)
    with open(train_val_txtPath, 'w') as wf:
        for i in range(len(imgs)):
            text = imgs[i].split(".jpg")[0] +'\n'
            wf.write(text)

三 将yolo格式的标注文件.txt转换为coco格式的标注文件.json

import argparse
import json
import os
import sys
import shutil
from datetime import datetime

import cv2

coco = dict()
coco['images'] = []
coco['type'] = 'instances'
coco['annotations'] = []
coco['categories'] = []

category_set = dict()
image_set = set()

image_id = 000000
annotation_id = 0


def addCatItem(category_dict):
    for k, v in category_dict.items():
        category_item = dict()
        category_item['supercategory'] = 'none'
        category_item['id'] = int(k)
        category_item['name'] = v
        coco['categories'].append(category_item)


def addImgItem(file_name, size):
    global image_id
    image_id += 1
    image_item = dict()
    image_item['id'] = image_id
    image_item['file_name'] = file_name
    image_item['width'] = size[1]
    image_item['height'] = size[0]
    image_item['license'] = None
    image_item['flickr_url'] = None
    image_item['coco_url'] = None
    image_item['date_captured'] = str(datetime.today())
    coco['images'].append(image_item)
    image_set.add(file_name)
    return image_id


def addAnnoItem(object_name, image_id, category_id, bbox):
    global annotation_id
    annotation_item = dict()
    annotation_item['segmentation'] = []
    seg = []
    # bbox[] is x,y,w,h
    # left_top
    seg.append(bbox[0])
    seg.append(bbox[1])
    # left_bottom
    seg.append(bbox[0])
    seg.append(bbox[1] + bbox[3])
    # right_bottom
    seg.append(bbox[0] + bbox[2])
    seg.append(bbox[1] + bbox[3])
    # right_top
    seg.append(bbox[0] + bbox[2])
    seg.append(bbox[1])

    annotation_item['segmentation'].append(seg)

    annotation_item['area'] = bbox[2] * bbox[3]
    annotation_item['iscrowd'] = 0
    annotation_item['ignore'] = 0
    annotation_item['image_id'] = image_id
    annotation_item['bbox'] = bbox
    annotation_item['category_id'] = category_id
    annotation_id += 1
    annotation_item['id'] = annotation_id
    coco['annotations'].append(annotation_item)


def xywhn2xywh(bbox, size):
    bbox = list(map(float, bbox))
    size = list(map(float, size))
    xmin = (bbox[0] - bbox[2] / 2.) * size[1]
    ymin = (bbox[1] - bbox[3] / 2.) * size[0]
    w = bbox[2] * size[1]
    h = bbox[3] * size[0]
    box = (xmin, ymin, w, h)
    return list(map(int, box))


def parseXmlFilse(image_path, anno_path, save_path, json_name='train.json'):
    assert os.path.exists(image_path), "ERROR {} dose not exists".format(image_path)
    assert os.path.exists(anno_path), "ERROR {} dose not exists".format(anno_path)
    if os.path.exists(save_path):
        pass
        # shutil.rmtree(save_path)
    os.makedirs(save_path)
    json_path = os.path.join(save_path, json_name)

    category_set = []
    with open(anno_path + '/classes.txt', 'r') as f:
        for i in f.readlines():
            category_set.append(i.strip())
    category_id = dict((k, v) for k, v in enumerate(category_set))
    addCatItem(category_id)

    images = [os.path.join(image_path, i) for i in os.listdir(image_path)]
    files = [os.path.join(anno_path, i) for i in os.listdir(anno_path)]
    images_index = dict((v.split(os.sep)[-1][:-4], k) for k, v in enumerate(images))
    for file in files:
        if os.path.splitext(file)[-1] != '.txt' or 'classes' in file.split(os.sep)[-1]:
            continue
        if file.split(os.sep)[-1][:-4] in images_index:
            index = images_index[file.split(os.sep)[-1][:-4]]
            img = cv2.imread(images[index])
            shape = img.shape
            filename = images[index].split(os.sep)[-1]
            current_image_id = addImgItem(filename, shape)

        else:
            continue
        with open(file, 'r') as fid:
            for i in fid.readlines():
                i = i.strip().split()
                category = int(i[0])
                category_name = category_id[category]
                bbox = xywhn2xywh((i[1], i[2], i[3], i[4]), shape)
                addAnnoItem(category_name, current_image_id, category, bbox)

    json.dump(coco, open(json_path, 'w'))
    print("class nums:{}".format(len(coco['categories'])))
    print("image nums:{}".format(len(coco['images'])))
    print("bbox nums:{}".format(len(coco['annotations'])))





def MultTxt2SingleJson():
    """
        脚本说明：
            本脚本用于将yolo格式的标注文件.txt转换为coco格式的标注文件.json
        参数说明：
            anno_path:标注文件txt存储路径
            save_path:json文件输出的文件夹
            image_path:图片路径
            json_name:json文件名字
        """
    parser = argparse.ArgumentParser()
    parser.add_argument('-ap', '--anno-path', type=str, default=r'D:\yolov5train\datasTrain3_More\labels\val', help='yolo txt path')
    parser.add_argument('-s', '--save-path', type=str, default=r'D:\yolov5train\datasTrain3_More\images\Annotations', help='json save path')
    parser.add_argument('--image-path', default=r'D:\yolov5train\datasTrain3_More\images\val')
    parser.add_argument('--json-name', default='val.json')

    opt = parser.parse_args()
    if len(sys.argv) > 1:
        print(opt)
        parseXmlFilse(**vars(opt))
    else:
        anno_path = r'D:\yolov5train\datasTrain3_More\labels\val'
        save_path = r'D:\yolov5train\datasTrain3_More\images\Annotations'
        image_path = r'D:\yolov5train\datasTrain3_More\images\val'
        json_name = 'val.json'
        parseXmlFilse(image_path, anno_path, save_path, json_name)
    pass

四 写入txt文件 分别存放训练集和验证集图片的路径

def writeImgPath_forYolov7Datas():
    '''
    因为yolov7训练的时候，在数据集根目录下，需要有txt文件分别存放训练集和验证集图片的路径
    '''
    from tqdm import tqdm
    import os
    imgpath = r'D:/yolov5train/datasTrain3_More/images/train'
    txt_path_name = r'D:/yolov5train/datasTrain3_More/train_list.txt'
    files = os.listdir(imgpath)
    imgspath = []
    for i in tqdm(range(len(files)), desc='进度 '):
        f = files[i]
        try:
            name = os.path.join(imgpath, f)
            name = name + '\n'
            imgspath.append(name)
        except Exception as e:
            print(f, ":", e)
            continue
    imgspath[-1] = imgspath[-1].replace('\n', '')
    with open(txt_path_name, 'w', encoding='utf-8') as wf:
        wf.writelines(imgspath)

五labelme的json转为yolo的txt

def labelmejson2yolotxt():
    import os
    import numpy as np
    from tqdm import tqdm

    imgPath = r' '
    jsonPath = r' '
    savetxtPath = r' '
    clsStatic, clsStaticFlag= {
    
    }, True
    # 先统计标签有哪些再保存txt，根据统计的标签 好确定 namell
    savetxtPath, savetxtPathFlag = savetxtPath, True
    # name15label = [pedes0, car1, bus2, truck3, bike4, elec5, tricycle6, coni7, warm8, tralight9, polic10, ambu11,
    #                fireen12, suv13, mpv14]
    name15 = {
    
    'car': 1, 'suv': 13, 'mpv': 14, 'van': 14, 'polic': 10, 'smatru': 3, 'elec': 5,
              'pedes': 0, 'coni': 7, 'tank': 3, 'moto': 5, 'bigtru': 3, 'bus': 2, 'engine': 3,
              'tricycle': 6, 'pickup': 1, 'coach': 2, 'bike': 4, 'pedesr': 0, 'crane': 3, 'trailer': 3,
              'excava': 3, 'warm': 8, 'tralight': 9, 'truck': 3, 'bigtrur': 3, 'vcar': 1, 'escort': 3 }
    namell =  name15


    files = os.listdir(imgPath)
    print('len(imgPath): ', len(files))
    # files = [x for x in files if x[-4:] == '.jpg']

    for i in tqdm(range(len(files)), desc='进度：'):
        f = files[i]

        if (f[-4:] != '.jpg'):
            continue
        imgShape = cv2.imread(os.path.join(imgPath, f)).shape
        imgw, imgh = imgShape[1], imgShape[0]

        json_path_name = os.path.join(jsonPath, f[:-4] + '.json')
        with open(json_path_name, 'r', encoding='utf-8') as rf:
            rf = json.load(rf)

            try:
                objs = rf['shapes']
            except:
                continue

            boxs = []
            for o in objs:
                try:
                    id = o['label']
                    if clsStaticFlag:
                        if id in clsStatic.keys():
                            clsStatic[id] += 1
                        else:
                            clsStatic[id] = 1
                    if savetxtPathFlag:
                        if id not in namell.keys():
                            continue
                        id = str(namell[id])

                        xmin = o['points'][0][0]
                        ymin = o['points'][0][1]
                        xmax = o['points'][1][0]
                        ymax = o['points'][1][1]

                        ymax = imgh if (ymax > imgh or (imgh - ymax < 5)) else ymax
                        ymin = 0 if ymin < 5 else ymin
                        xmax = imgw if (xmax > imgw or (imgw - xmax < 5)) else xmax
                        xmin = 0 if xmin < 5 else xmin
                        x = (xmin + xmax) / 2 / imgw
                        y = (ymin + ymax) / 2 / imgh
                        w = (xmax - xmin) / imgw
                        h = (ymax - ymin) / imgh
                        x = str(x) if len(str(x)) <= 7 else str(x)[:7]
                        y = str(y) if len(str(y)) <= 7 else str(y)[:7]
                        w = str(w) if len(str(w)) <= 7 else str(w)[:7]
                        h = str(h) if len(str(h)) <= 7 else str(h)[:7]
                        box = id + ' ' + x + ' ' + y + ' ' + w + ' ' + h + '\n'
                        boxs.append(box)
                except Exception as e:
                    print('jie Xi Json Error: ', e)
                    continue
            if boxs == [] and savetxtPathFlag == True:
                continue

        if savetxtPathFlag:
            boxs[-1] = boxs[-1].replace('\n', '')
            txt_path_name = os.path.join(savetxtPath, f[:-4] + '.txt')
            with open(txt_path_name, 'w', encoding='utf-8') as wf:
                wf.writelines(boxs)
    if clsStaticFlag:
        print('clsStatic: ', clsStatic)

        # break