关于yolov8识别滑块关键点

1，images,annotations创建

IMAGES：放图片材料的

ANNTATIONS：放labelImg标记的xml文件

2，labels,txt怎么来的

labels ：可以手动创建，里面还配置了train,val,test文件夹。可手动（以下代码中没有写）

txt:由一下代码自动生成，前提是images,annotations需要自己去创建

3，xml2txt.py

images,annotations有了之后直接运行一下代码

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

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__":
    postfix = 'jpg'
    imgpath = 'VOCdevkit/images'
    xmlpath = 'VOCdevkit/annnotations'
    txtpath = 'VOCdevkit/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}')

4，split_data.py

此文件是以上代码执行完毕执行，前提需要有labels文件夹

import os, shutil, random
random.seed(0)
import numpy as np
source_path=r'D:/BRWork/ultralytics-main/datesets/VOCdevkit/'
val_size = 0.1
test_size = 0.2
postfix = 'jpg'
imgpath = source_path+'images'
txtpath = source_path+'txt'

os.makedirs('VOCdevkit/images/train', exist_ok=True)
os.makedirs('VOCdevkit/images/val', exist_ok=True)
os.makedirs('VOCdevkit/images/test', exist_ok=True)
os.makedirs('labels/train', exist_ok=True)
os.makedirs('labels/val', exist_ok=True)
os.makedirs('labels/test', exist_ok=True)

listdir = np.array([i for i in os.listdir(txtpath) if 'txt' in i])
print(listdir)
random.shuffle(listdir)
train, val, test = listdir[:int(len(listdir) * (1 - val_size - test_size))], listdir[int(len(listdir) * (1 - val_size - test_size)):int(len(listdir) * (1 - test_size))], listdir[int(len(listdir) * (1 - test_size)):]
print(f'train set size:{len(train)} val set size:{len(val)} test set size:{len(test)}')

for i in train:
    shutil.copy('{}/{}.{}'.format(imgpath, i[:-4], postfix), source_path+'images/train/{}.{}'.format(i[:-4], postfix))
    shutil.copy('{}/{}'.format(txtpath, i), source_path+'labels/train/{}'.format(i))

for i in val:
    shutil.copy('{}/{}.{}'.format(imgpath, i[:-4], postfix), source_path+'images/val/{}.{}'.format(i[:-4], postfix))
    shutil.copy('{}/{}'.format(txtpath, i), source_path+'labels/val/{}'.format(i))

for i in test:
    shutil.copy('{}/{}.{}'.format(imgpath, i[:-4], postfix), source_path+'images/test/{}.{}'.format(i[:-4], postfix))
    shutil.copy('{}/{}'.format(txtpath, i), source_path+'labels/test/{}'.format(i))

5，路径问题

以上文件路径自定义修改

6，文件运行不起来的问题data.yaml

全部写成绝对路径：

train: D:\BRWork\ultralytics-main\datesets\VOCdevkit\images\train
val: D:\BRWork\ultralytics-main\datesets\VOCdevkit\images\test
test: D:\BRWork\ultralytics-main\datesets\VOCdevkit\images\test

nc: 2

names: ['crack1', 'crack2']

7.运行文件，训练

也需要写成绝对路径。我的是cpu训练的，gpu训练自行调整

from ultralytics import YOLO

# model = YOLO("../yolov8n.pt")
#
# results = model.train(data=r"D:\BRWork\ultralytics-main\data.yaml", imgsz=320, epochs=120, batch=16, device='cpu', workers=0)