yolov5训练自己的数据集

1.安装cuda

　　可以先看看自己的显卡信息，支持哪个cuda版本

　　cuda下载地址：https://developer.nvidia.com/cuda-toolkit-archive

　　我的RTX3060，下载的cuda11.8

　　下载后安装，直接默认安装到底，然后打开cmd，输入nvcc -V

　2.安装cudnn

　　需要安装和cuda版本对应的cudnn

　　地址：https://developer.nvidia.com/rdp/cudnn-archive

　　下载对应的版本，解压替换到cuda安装目录下

3.安装Pytorch

　　我使用的是conda默认的环境，python3.9

　　进入pytorch官网：https://pytorch.org/

　　找到对应的版本下载，我这里不指定torch版本，直接运行

　　pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

　　等待安装完成即可

4.安装标注软件

　　pip install labelImg

　　安装成功后直接运行 labelImg 打开软件

　　open dir打开图片文件夹，change save dir 选择保存的xml文件的文件夹

　　create rectBox去框选需要检测的目标，输入label name

　　标注完自己的数据

　　一个img图片文件夹，一个和图片对应的xml文件夹

5. 将数据集进行分割

　　执行下面代码，即可得到分割好的数据集

import os
import random
import shutil

img_path = 'img'
xml_path = 'xml'



def split_file_name(file_name):
    f_name, _ = file_name.split('.')
    return f_name


def split_move_file(target_path, save_basic_path, train_scale=0.9):
    train_img_path = os.path.join(save_basic_path, 'images/train')
    train_xml_path = os.path.join(save_basic_path, 'xml/train')
    val_img_path = os.path.join(save_basic_path, 'images/val')
    val_xml_path = os.path.join(save_basic_path, 'xml/val')
    print(save_basic_path, train_img_path)
    if not os.path.exists(train_img_path):
        os.makedirs(train_img_path)
    if not os.path.exists(train_xml_path):
        os.makedirs(train_xml_path)
    if not os.path.exists(val_img_path):
        os.makedirs(val_img_path)
    if not os.path.exists(val_xml_path):
        os.makedirs(val_xml_path)


    img_file_path = os.path.join(target_path, img_path)
    file_list = os.listdir(img_file_path)
    # print(file_list)
    # 得到名字列表
    file_name_li = list(map(lambda x: split_file_name(x), file_list))
    random.shuffle(file_name_li)
    # print(file_name_li)
    train_ind = int(len(file_name_li) * train_scale)
    train_data = file_name_li[:train_ind]
    val_data = file_name_li[train_ind:]
    print('total number', len(file_name_li))
    print('train number', len(train_data))
    print('val number', len(val_data))

    for file in train_data:

        file_path = os.path.join(img_file_path, file+'.jpg')
        save_path = os.path.join(train_img_path, file+'.jpg')
        if not os.path.exists(file_path):
            file_path = os.path.join(img_file_path, file + '.jpeg')
            save_path = os.path.join(train_img_path, file + '.jpg')
            if not os.path.exists(file_path):
                file_path = os.path.join(img_file_path, file + '.png')
                save_path = os.path.join(train_img_path, file + '.png')
        if os.path.exists(file_path):
            shutil.copyfile(file_path, save_path)

        # xml文件
        xml_file_path = os.path.join(target_path, xml_path)
        file_path = os.path.join(xml_file_path, file + '.xml')
        save_path = os.path.join(train_xml_path, file + '.xml')
        if os.path.exists(file_path):
            shutil.copyfile(file_path, save_path)
    for file in val_data:

        file_path = os.path.join(img_file_path, file+'.jpg')
        save_path = os.path.join(val_img_path, file+'.jpg')
        if not os.path.exists(file_path):
            file_path = os.path.join(img_file_path, file + '.jpeg')
            save_path = os.path.join(val_img_path, file + '.jpg')
            if not os.path.exists(file_path):
                file_path = os.path.join(img_file_path, file + '.png')
                save_path = os.path.join(val_img_path, file + '.png')
        if os.path.exists(file_path):
            shutil.copyfile(file_path, save_path)

        # xml文件
        xml_file_path = os.path.join(target_path, xml_path)
        file_path = os.path.join(xml_file_path, file + '.xml')
        save_path = os.path.join(val_xml_path, file + '.xml')
        if os.path.exists(file_path):
            shutil.copyfile(file_path, save_path)


if __name__ == '__main__':

    target_path = r'C:\Users\mojia\Desktop\maizi\maozi20230326'
    save_basic_path = r'C:\Users\mojia\Desktop\maizi\maozi20230326_train_val'
    if not os.path.exists(save_basic_path):
        os.mkdir(save_basic_path)
    scale = 0.9     # 训练集比例
    split_move_file(target_path, save_basic_path, scale)

6. 将标注的xml文件转换为txt文件格式

import xml.etree.ElementTree as ET

import os





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
    if w >= 1:
        w = 0.99
    if h >= 1:
        h = 0.99
    return (x, y, w, h)

folder_li = ['train', 'val']
def convert_annotation(rootpath, classes):
    labelpath = rootpath + '/labels'  # 生成的.txt文件会被保存在labels目录下
    if not os.path.exists(labelpath):
        os.makedirs(labelpath)
    for folder in folder_li:
        xmlpath = rootpath + '/xml/'+folder
        file_list = os.listdir(xmlpath)
        for xmlname in file_list:
            xmlfile = os.path.join(xmlpath, xmlname)
            with open(xmlfile, "r", encoding='UTF-8') as in_file:
                txtname = xmlname[:-4] + '.txt'
                # print(txtname)
                txtpath = labelpath + '/' + folder
                if not os.path.exists(txtpath):
                    os.makedirs(txtpath)
                txtfile = os.path.join(txtpath, txtname)
                with open(txtfile, "w+", encoding='UTF-8') as out_file:
                    tree = ET.parse(in_file)
                    root = tree.getroot()
                    size = root.find('size')
                    w = int(size.find('width').text)
                    h = int(size.find('height').text)
                    out_file.truncate()
                    for obj in root.iter('object'):
                        difficult = obj.find('difficult').text
                        cls = obj.find('name').text
                        if cls not in classes or int(difficult) == 1:
                            continue
                        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)
                        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


if __name__ == "__main__":
    rootpath = r'C:\Users\mojia\Desktop\maizi\maozi20230326_train_val'
    # 数据标签
    classes = ['帽子']  # 需要修改
    convert_annotation(rootpath, classes)