手把手教你训练自己的YOLOv7

1.数据的制作

 

 （1）将标注好的VOC数据，转YOLO数据集：代码来自labelimg标注的VOC格式标签xml文件和yolo格式标签txt文件相互转换_炮哥带你学的博客-CSDN博客_voc标签

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 = ['0', '1']
    # 2、voc格式的xml标签文件路径
    xml_files1 = r'D:\yolov7-1114\data\mydata\xml'
    # 3、转化为yolo格式的txt标签文件存储路径
    save_txt_files1 = r'D:\yolov7-1114\data\mydata\label'

    convert_annotation(xml_files1, save_txt_files1, classes1)

（2）划分数据集：来自Yolov7训练自己的数据集（超详细）_boligongzhu的博客-CSDN博客

# 将图片和标注数据按比例切分为 训练集和测试集
import shutil
import random
import os

# 原始路径
image_original_path = "D:/yolov7-1114/data/mydata/images/"      # 原始图片位置
label_original_path = r"D:/yolov7-1114/data/mydata/label/"      # VOC转COCO数据集的位置

cur_path = os.getcwd()

# 训练集路径
train_image_path = os.path.join(cur_path, "datasets/defect/images/train/")
train_label_path = os.path.join(cur_path, "datasets/defect/labels/train/")

# 验证集路径
val_image_path = os.path.join(cur_path, "datasets/defect/images/val/")
val_label_path = os.path.join(cur_path, "datasets/defect/labels/val/")

# 测试集路径
test_image_path = os.path.join(cur_path, "datasets/defect/images/test/")
test_label_path = os.path.join(cur_path, "datasets/defect/labels/test/")

# 训练集目录
list_train = os.path.join(cur_path, "datasets/defect/train.txt")
list_val = os.path.join(cur_path, "datasets/defect/val.txt")
list_test = os.path.join(cur_path, "datasets/defect/test.txt")

train_percent = 0.6
val_percent = 0.2
test_percent = 0.2


def del_file(path):
    for i in os.listdir(path):
        file_data = path + "\\" + i
        os.remove(file_data)


def mkdir():
    if not os.path.exists(train_image_path):
        os.makedirs(train_image_path)
    else:
        del_file(train_image_path)
    if not os.path.exists(train_label_path):
        os.makedirs(train_label_path)
    else:
        del_file(train_label_path)

    if not os.path.exists(val_image_path):
        os.makedirs(val_image_path)
    else:
        del_file(val_image_path)
    if not os.path.exists(val_label_path):
        os.makedirs(val_label_path)
    else:
        del_file(val_label_path)

    if not os.path.exists(test_image_path):
        os.makedirs(test_image_path)
    else:
        del_file(test_image_path)
    if not os.path.exists(test_label_path):
        os.makedirs(test_label_path)
    else:
        del_file(test_label_path)


def clearfile():
    if os.path.exists(list_train):
        os.remove(list_train)
    if os.path.exists(list_val):
        os.remove(list_val)
    if os.path.exists(list_test):
        os.remove(list_test)


def main():
    mkdir()
    clearfile()

    file_train = open(list_train, 'w')
    file_val = open(list_val, 'w')
    file_test = open(list_test, 'w')

    total_txt = os.listdir(label_original_path)
    num_txt = len(total_txt)
    list_all_txt = range(num_txt)

    num_train = int(num_txt * train_percent)
    num_val = int(num_txt * val_percent)
    num_test = num_txt - num_train - num_val

    train = random.sample(list_all_txt, num_train)
    # train从list_all_txt取出num_train个元素
    # 所以list_all_txt列表只剩下了这些元素
    val_test = [i for i in list_all_txt if not i in train]
    # 再从val_test取出num_val个元素，val_test剩下的元素就是test
    val = random.sample(val_test, num_val)

    print("训练集数目：{}, 验证集数目：{}, 测试集数目：{}".format(len(train), len(val), len(val_test) - len(val)))
    for i in list_all_txt:
        name = total_txt[i][:-4]

        srcImage = image_original_path + name + '.bmp'
        srcLabel = label_original_path + name + ".txt"

        if i in train:
            dst_train_Image = train_image_path + name + '.bmp'
            dst_train_Label = train_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_train_Image)
            shutil.copyfile(srcLabel, dst_train_Label)
            file_train.write(dst_train_Image + '\n')
        elif i in val:
            dst_val_Image = val_image_path + name + '.bmp'
            dst_val_Label = val_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_val_Image)
            shutil.copyfile(srcLabel, dst_val_Label)
            file_val.write(dst_val_Image + '\n')
        else:
            dst_test_Image = test_image_path + name + '.bmp'
            dst_test_Label = test_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_test_Image)
            shutil.copyfile(srcLabel, dst_test_Label)
            file_test.write(dst_test_Image + '\n')

    file_train.close()
    file_val.close()
    file_test.close()


if __name__ == "__main__":
    main()

2.代码的修改

（1）修改配置文件

 （2）修改训练文件

 训练就可以啦