YOLOv8-Detect训练自己的数据集

​

​

​

​

import argparse, json
import cytoolz
from lxml import etree, objectify
import os, re

def instance2xml_base(anno):
    E = objectify.ElementMaker(annotate=False)
    anno_tree = E.annotation(
        E.folder('VOC2014_instance/{}'.format(anno['category_id'])),
        E.filename(anno['file_name']),
        E.source(
            E.database('MS COCO 2014'),
            E.annotation('MS COCO 2014'),
            E.image('Flickr'),
            E.url(anno['coco_url'])
        ),
        E.size(
            E.width(anno['width']),
            E.height(anno['height']),
            E.depth(3)
        ),
        E.segmented(0),
    )
    return anno_tree

def instance2xml_bbox(anno, bbox_type='xyxy'):
    """bbox_type: xyxy (xmin, ymin, xmax, ymax); xywh (xmin, ymin, width, height)"""
    assert bbox_type in ['xyxy', 'xywh']
    if bbox_type == 'xyxy':
        xmin, ymin, w, h = anno['bbox']
        xmax = xmin+w
        ymax = ymin+h
    else:
        xmin, ymin, xmax, ymax = anno['bbox']
    E = objectify.ElementMaker(annotate=False)
    anno_tree = E.object(
        E.name(anno['category_id']),
        E.bndbox(
            E.xmin(xmin),
            E.ymin(ymin),
            E.xmax(xmax),
            E.ymax(ymax)
        ),
        E.difficult(anno['iscrowd'])
    )
    return anno_tree


def parse_instance(content, outdir):
    # print('11111',content)
    categories = {d['id']: d['name'] for d in content['categories']}
    # merge images and annotations: id in images vs image_id in annotations
    merged_info_list = list(map(cytoolz.merge, cytoolz.join('id', content['images'], 'image_id', content['annotations'])))

    # print('111111111111',merged_info_list)
    # convert category id to name
    for instance in merged_info_list:
        instance['category_id'] = categories[instance['category_id']]
    # group by filename to pool all bbox in same file
    for name, groups in cytoolz.groupby('file_name', merged_info_list).items():
        anno_tree = instance2xml_base(groups[0])
        # if one file have multiple different objects, save it in each category sub-directory
        filenames = []
        # print(groups)
        for group in groups:
            filenames.append(os.path.join(outdir, re.sub(" ", "_", group['category_id']), os.path.splitext(name)[0] + ".xml"))
            anno_tree.append(instance2xml_bbox(group, bbox_type='xyxy'))
        for filename in filenames:
            etree.ElementTree(anno_tree).write(filename, pretty_print=True)
        print("Formating instance xml file {} done!".format(name))

def main(args):
    if not os.path.exists(args.output_dir):
        os.makedirs(args.output_dir)
    content = json.load(open(args.anno_file, 'r'))
    if args.type == 'instance':
        # make subdirectories
        sub_dirs = [re.sub(" ", "_", cate['name']) for cate in content['categories']]
        for sub_dir in sub_dirs:
            sub_dir = os.path.join(args.output_dir, str(sub_dir))
            if not os.path.exists(sub_dir):
                os.makedirs(sub_dir)
        parse_instance(content, args.output_dir)



if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--anno_file", help="annotation file for object instance/keypoint", default=r'D:\CoCoData\annotations_14_17\instances_train2017.json')
    parser.add_argument("--type", type=str, default='instance', help="object instance or keypoint", choices=['instance', 'keypoint'])
    parser.add_argument("--output_dir", help="output directory for voc annotation xml file", default=r'D:\CoCoData\CoCoXml')
    args = parser.parse_args()
    main(args)

import os
import random
import xml.etree.ElementTree as ET

import glob


classes = ['person', 'cat', 'dog']

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 = min(size[0],box[2] - box[0])
    h = min(size[1],box[3] - box[1])
    # print(x,y,w,h)
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)
def convert_annotation(xml, list_file):
    in_file = open(os.path.join(xml), encoding='utf-8')
    tree = ET.parse(in_file)
    root = tree.getroot()


    xmlsize = root.find('size')
    w = int(xmlsize.find('width').text)
    h = int(xmlsize.find('height').text)
    # print(w,h)

    for obj in root.iter('object'):
        difficult = 0
        if obj.find('difficult') != None:
            difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            print(cls, "------------------------------------\n")
            continue
        cls_id = classes.index(cls)
        print(cls, cls_id)
        xmlbox = obj.find('bndbox')
        x0 = float(xmlbox.find('xmin').text)
        y0 = float(xmlbox.find('ymin').text)
        x1 = float(xmlbox.find('xmax').text)
        y1 = float(xmlbox.find('ymax').text)
        xmin = min(x0, x1)
        ymin = min(y0, y1)
        xmax = max(x0, x1)
        ymax = max(y0, y1)

        # b = (int(xmin), int(ymin), int(xmax), int(ymax))
        b = (float(xmin), float(ymin), float(xmax), float(ymax))
        # print(b)
        bb = convert((w, h), b)
        # print(bb)

        list_file.write(" "+str(cls_id) +"," + ",".join([str(a) for a in bb]))


if __name__ == "__main__":
    random.seed(0)

    # 图片路径
    cocoImgPath = r'D:\Yolov8\Yolov8_dataset\selfXml\err04'
    # Xml路径
    cocoXmlPath = r'D:\Yolov8\Yolov8_dataset\selfXml\err04'
    #txt保存路径
    txtsavepath = r'D:\Yolov8\ultralytics-main\datasets\mydata\selfv8txt'
    fileWriteTxt = txtsavepath + '\\'+ cocoImgPath.split('\\')[-1] + '_v8.txt'
    xmls = glob.glob(os.path.join(cocoXmlPath, '*.xml'))
    list_file = open(fileWriteTxt, 'w', encoding='utf-8')

    for xml in xmls:
        img = xml.replace(cocoXmlPath, cocoImgPath).replace('.xml', '.jpg')
        if not os.path.exists(img):
            print(img, ' is not exit')
            continue
        list_file.write(img)
        convert_annotation(xml, list_file)
        list_file.write('\n')
    list_file.close()

import glob
import os


#批量处理，txt存放文件夹
txtpathdir = r'D:\Yolov8\ultralytics-main\datasets\mydata\selfv8txt\err04_v8.txt'
#保存txt路径
savetxtpath = r'D:\Yolov8\ultralytics-main\datasets\mydata\labels\train'


file = open(txtpathdir,'r',encoding='utf-8')
lines = file.readlines()
for line in lines:
    line = line.split('\n')[0]
    # print(line)
    imgdir = line.split(' ')[0]
    bboxinfo = line.split(' ')[1:]
    # print('imgdir',imgdir)
    savetxtdir = os.path.join(savetxtpath,imgdir.split('\\')[-1].replace('.jpg','.txt'))
    file = open(savetxtdir, 'w', encoding='utf-8')
    # print(savetxtdir)
    for i in range(len(bboxinfo)):
        # print(bboxinfo[i])
        info = bboxinfo[i].split(',')
        # print(info)
        info1 = ' '.join(info)
        print(info1)
        file.write(info1+'\n')

import glob
import os
import shutil

txtpathdir = r'D:\Yolov8\ultralytics-main\datasets\mydata\cocotxt\train2017_v8.txt'
saveimgpath = r'D:\Yolov8\ultralytics-main\datasets\mydata\images\train'
file = open(txtpathdir,'r',encoding='utf-8')
lines = file.readlines()
for line in lines:
    line = line.split('\n')[0]
    imgdir = line.split(' ')[0]
    print('imgdir',imgdir)
    saveimgdir = os.path.join(saveimgpath,imgdir.split('\\')[-1])
    print(saveimgdir)

    shutil.copy(imgdir,saveimgdir)