目标检测：yolov7训练自己的数据集，新手小白也能学会训练模型，一看就会

conda create -n labelimg python=3.8

conda activate labelimg

pip install labelimg -i https://pypi.tuna.tsinghua.edu.cn/simple

labelimg JPEGImages classes.txt

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
 
 
def convert(size, box):
    x_center = (box[0] + box[1]) / 2.0
    y_center = (box[2] + box[3]) / 2.0
    x = x_center / size[0]
    y = y_center / size[1]
    w = (box[1] - box[0]) / size[0]
    h = (box[3] - box[2]) / size[1]
    return (x, y, w, h)
 
 
def convert_annotation(xml_files_path, save_txt_files_path, classes):
    xml_files = os.listdir(xml_files_path)
    print(xml_files)
    for xml_name in xml_files:
        print(xml_name)
        xml_file = os.path.join(xml_files_path, xml_name)
        out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
        out_txt_f = open(out_txt_path, 'w')
        tree = ET.parse(xml_file)
        root = tree.getroot()
        size = root.find('size')
        w = int(size.find('width').text)
        h = int(size.find('height').text)
 
        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))
            # b=(xmin, xmax, ymin, ymax)
            print(w, h, b)
            bb = convert((w, h), b)
            out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
 
 
if __name__ == "__main__":
    # 需要转换的类别，需要一一对应
    classes1 = ['hat','nohat']
    # 2、voc格式的xml标签文件路径
    xml_files1 = r'f:\data\Annotations'
    # 3、转化为yolo格式的txt标签文件存储路径
    save_txt_files1 = r'f:\data\labels'
 
    convert_annotation(xml_files1, save_txt_files1, classes1)

import os
import shutil
import random
 
random.seed(0)
 
 
def split_data(file_path,xml_path, new_file_path, train_rate, val_rate, test_rate):
    each_class_image = []
    each_class_label = []
    for image in os.listdir(file_path):
        each_class_image.append(image)
    for label in os.listdir(xml_path):
        each_class_label.append(label)
    data=list(zip(each_class_image,each_class_label))
    total = len(each_class_image)
    random.shuffle(data)
    each_class_image,each_class_label=zip(*data)
    train_images = each_class_image[0:int(train_rate * total)]
    val_images = each_class_image[int(train_rate * total):int((train_rate + val_rate) * total)]
    test_images = each_class_image[int((train_rate + val_rate) * total):]
    train_labels = each_class_label[0:int(train_rate * total)]
    val_labels = each_class_label[int(train_rate * total):int((train_rate + val_rate) * total)]
    test_labels = each_class_label[int((train_rate + val_rate) * total):]
 
    for image in train_images:
        print(image)
        old_path = file_path + '/' + image
        new_path1 = new_file_path + '/' + 'train' + '/' + 'images'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)
 
    for label in train_labels:
        print(label)
        old_path = xml_path + '/' + label
        new_path1 = new_file_path + '/' + 'train' + '/' + 'labels'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)
 
    for image in val_images:
        old_path = file_path + '/' + image
        new_path1 = new_file_path + '/' + 'val' + '/' + 'images'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)
 
    for label in val_labels:
        old_path = xml_path + '/' + label
        new_path1 = new_file_path + '/' + 'val' + '/' + 'labels'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)
 
    for image in test_images:
        old_path = file_path + '/' + image
        new_path1 = new_file_path + '/' + 'test' + '/' + 'images'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)
 
    for label in test_labels:
        old_path = xml_path + '/' + label
        new_path1 = new_file_path + '/' + 'test' + '/' + 'labels'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)
 
 
if __name__ == '__main__':
    file_path = r"f:\data\JPEGImages"
    txt_path = r'f:\data\labels'
    new_file_path = r"f:\VOCdevkit"
    split_data(file_path,txt_path, new_file_path, train_rate=0.8, val_rate=0.2, test_rate=0.2)

# importing the os Library
import os
 
train_list = r'f:/VOCdevkit/train/images/'
val_list = r'f:/VOCdevkit/val/images/'
path_list1 = r'f:/VOCdevkit/train_list.txt'
path_list2 = r'f:/VOCdevkit/val_list.txt'
 
 
def findfiles(path,path_list):
    # 首先遍历当前目录所有文件及文件夹
    file_list = os.listdir(path)
    # 循环判断每个元素是否是文件夹还是文件，是文件夹的话，递归
    for file in file_list:
    	# 利用os.path.join()方法取得路径全名，并存入cur_path变量，否则每次只能遍历一层目录
        cur_path = os.path.join(path, file)
        # 判断是否是文件夹
        with open(path_list,'a') as f:
            f.write(cur_path+'\n')
            f.close()
 
if __name__ == '__main__':
    findfiles(train_list,path_list1)
    findfiles(val_list, path_list2)

train: f:/VOCdevkit/train_list.txt  # train images (relative to 'path') 128 images
val: f:/VOCdevkit/val_list.txt  # val images (relative to 'path') 128 images
 
nc: 2
 
# Classes
names: ['hat','nohat']