YOLO图像前处理及格式转换

import cv2
import numpy as np
import os
import glob

# 数据增强函数
def augment_data(img):
    rows,cols,_ = img.shape

    # 水平翻转图像
    if np.random.random() > 0.5:
        img = cv2.flip(img, 1)
        img_name = os.path.splitext(save_path)[0] + "_flip.png"
        cv2.imwrite(img_name, img)
        print("Saved augmented image:", img_name)

    # 随机缩放图像
    scale = np.random.uniform(0.9, 1.1)
    M = cv2.getRotationMatrix2D((cols/2, rows/2), 0, scale)
    img_transformed = cv2.warpAffine(img, M, (cols, rows))
    img_name = os.path.splitext(save_path)[0] + "_transform.png"
    cv2.imwrite(img_name, img_transformed)
    print("Saved augmented image:", img_name)

    # 随机旋转图像
    angle = np.random.randint(-10, 10)
    M = cv2.getRotationMatrix2D((cols/2, rows/2), angle, 1)
    img_rotated = cv2.warpAffine(img, M, (cols, rows))
    img_name = os.path.splitext(save_path)[0] + "_rotated.png"
    cv2.imwrite(img_name, img_rotated)
    print("Saved augmented image:", img_name)

    # 添加高斯噪音
    mean = 0
    std = np.random.uniform(5, 15)
    noise = np.zeros(img.shape, np.float32)
    cv2.randn(noise, mean, std)
    noise = np.uint8(noise)
    img_noisy = cv2.add(img, noise)
    img_name = os.path.splitext(save_path)[0] + "_noisy.png"
    cv2.imwrite(img_name, img_noisy)
    print("Saved augmented image:", img_name)

    # 随机调整对比度和亮度
    alpha = np.random.uniform(0.8, 1.2)
    beta = np.random.randint(-10, 10)
    img_contrast = cv2.convertScaleAbs(img, alpha=alpha, beta=beta)
    img_name = os.path.splitext(save_path)[0] + "_contrast.png"
    cv2.imwrite(img_name, img_contrast)
    print("Saved augmented image:", img_name)

    return img


# 读取 data 文件夹中的所有图片，并进行数据增强
data_dir = "data"
save_dir = "result"
if not os.path.exists(save_dir):
    os.makedirs(save_dir)

# 使用 glob 库来遍历 data 文件夹中所有图像
for img_path in glob.glob(os.path.join(data_dir, "*.png")):

    img = cv2.imread(img_path)

    # 获取保存增强后的图片文件名
    img_name = os.path.basename(img_path)
    save_path = os.path.join(save_dir, img_name)

    # 数据增强
    augment_data(img)

    # 保存原始图片
    cv2.imwrite(save_path, img)
    print("Saved original image:", save_path)

XML格式数据集转TXT（YOLO）_xml转txt-优快云博客

yolov8-制作数据集，数据集格式转换（yolo格式-voc格式）附完整代码_yolov8数据集格式-优快云博客

yolo图像检测数据集格式转换：xml 与 txt格式相互转换_yolo .csv文件转.xml文件-优快云博客

python 未解析的引用“lxml” - 优快云文库

import os
import xml.etree.ElementTree as ET

# 定义类别列表
classes = ["crack", "porosity", "normal"]  # 根据您的数据集进行修改

# 输入和输出文件夹路径
xml_folder = "F:/train/Annotations"
txt_folder = "F:/train/labels"
os.makedirs(txt_folder, exist_ok=True)

# 解析XML文件并转换为YOLO格式
for xml_file in os.listdir(xml_folder):
    if xml_file.endswith(".xml"):
        # 解析XML
        tree = ET.parse(os.path.join(xml_folder, xml_file))
        root = tree.getroot()

        txt_file_path = os.path.join(txt_folder, os.path.splitext(xml_file)[0] + ".txt")
        with open(txt_file_path, "w") as txt_file:
            for obj in root.findall("object"):
                # 提取类别、边界框信息
                class_name = obj.find("name").text
                if class_name not in classes:
                    continue
                class_id = classes.index(class_name)

                bbox = obj.find("bndbox")
                xmin = int(bbox.find("xmin").text)
                ymin = int(bbox.find("ymin").text)
                xmax = int(bbox.find("xmax").text)
                ymax = int(bbox.find("ymax").text)

                # 计算边界框中心点和宽高
                width = xmax - xmin
                height = ymax - ymin
                x_center = (xmin + xmax) / 2
                y_center = (ymin + ymax) / 2

                # 归一化坐标
                img_width = int(root.find("size").find("width").text)
                img_height = int(root.find("size").find("height").text)
                x_center /= img_width
                y_center /= img_height
                width /= img_width
                height /= img_height

                # 写入TXT文件
                txt_file.write(f"{class_id} {x_center:.6f} {y_center:.6f} {width:.6f} {height:.6f}\n")

print("转换完成！")