python：VOC格式数据集转换为YOLO数据集格式

这篇文章介绍了python：VOC格式数据集转换为YOLO数据集格式，分享给大家做个参考，收藏Python资料网收获更多编程知识

作者：CSDN @ _养乐多_

本文将介绍如何将目标检测中常用的VOC格式数据集转换为YOLO数据集，并进行数据集比例划分，从而方便的进行YOLO目标检测。

如果不想分两步，可以直接看第三节代码。

---

---

一、将VOC格式数据集转换为YOLO格式数据集

执行以下脚本将VOC格式数据集转换为YOLO格式数据集。
但是需要注意的是：

1. 转换之后的数据集只有Images和labels两个文件。还需要执行第二节中的脚本进行数据集划分，将总的数据集划分为训练、验证、测试数据集；
2. 使用的话，需要修改 class_mapping 中类别名和对应标签，还有VOC数据集路径、YOLO数据集路径。

import os
import shutil
import xml.etree.ElementTree as ET

# VOC格式数据集路径
voc_data_path = 'E:\\DataSet\\helmet-VOC'
voc_annotations_path = os.path.join(voc_data_path, 'Annotations')
voc_images_path = os.path.join(voc_data_path, 'JPEGImages')

# YOLO格式数据集保存路径
yolo_data_path = 'E:\\DataSet\\helmet-YOLO'
yolo_images_path = os.path.join(yolo_data_path, 'images')
yolo_labels_path = os.path.join(yolo_data_path, 'labels')

# 创建YOLO格式数据集目录
os.makedirs(yolo_images_path, exist_ok=True)
os.makedirs(yolo_labels_path, exist_ok=True)

# 类别映射 (可以根据自己的数据集进行调整)
class_mapping = {
    'head': 0,
    'helmet': 1,
    'person': 2,
    # 添加更多类别...
}

def convert_voc_to_yolo(voc_annotation_file, yolo_label_file):
    tree = ET.parse(voc_annotation_file)
    root = tree.getroot()

    size = root.find('size')
    width = float(size.find('width').text)
    height = float(size.find('height').text)

    with open(yolo_label_file, 'w') as f:
        for obj in root.findall('object'):
            cls = obj.find('name').text
            if cls not in class_mapping:
                continue
            cls_id = class_mapping[cls]
            xmlbox = obj.find('bndbox')
            xmin = float(xmlbox.find('xmin').text)
            ymin = float(xmlbox.find('ymin').text)
            xmax = float(xmlbox.find('xmax').text)
            ymax = float(xmlbox.find('ymax').text)

            x_center = (xmin + xmax) / 2.0 / width
            y_center = (ymin + ymax) / 2.0 / height
            w = (xmax - xmin) / width
            h = (ymax - ymin) / height

            f.write(f"{cls_id} {x_center} {y_center} {w} {h}\n")

# 遍历VOC数据集的Annotations目录，进行转换
for voc_annotation in os.listdir(voc_annotations_path):
    if voc_annotation.endswith('.xml'):
        voc_annotation_file = os.path.join(voc_annotations_path, voc_annotation)
        image_id = os.path.splitext(voc_annotation)[0]
        voc_image_file = os.path.join(voc_images_path, f"{image_id}.jpg")
        yolo_label_file = os.path.join(yolo_labels_path, f"{image_id}.txt")
        yolo_image_file = os.path.join(yolo_images_path, f"{image_id}.jpg")

        convert_voc_to_yolo(voc_annotation_file, yolo_label_file)
        if os.path.exists(voc_image_file):
            shutil.copy(voc_image_file, yolo_image_file)

print("转换完成！")

二、YOLO格式数据集划分（训练、验证、测试）

参考：https://docs.ultralytics.com/datasets/detect/#ultralytics-yolo-format

随机将数据集按照0.7-0.2-0.1比例划分为训练、验证、测试数据集。
注意，修改代码中图片的后缀，如果是.jpg，就把.png修改为.jpg。

最终结果，

2.1 版本1

用版本1划分就行，不用版本2了。

import os
import shutil
import random
from math import floor


# 创建输出目录的函数
def create_dirs(output_dir):
    images_dir = os.path.join(output_dir, 'images')
    labels_dir = os.path.join(output_dir, 'labels')
    for split in ['train', 'val', 'test']:
        os.makedirs(os.path.join(images_dir, split), exist_ok=True)
        os.makedirs(os.path.join(labels_dir, split), exist_ok=True)
    return images_dir, labels_dir


# 获取图片和对应txt标签的列表
def get_files(images_path, labels_path):
    image_files = [f for f in os.listdir(images_path) if f.endswith(('jpg', 'png', 'jpeg'))]
    label_files = [f for f in os.listdir(labels_path) if f.endswith('.txt')]

    # 检查图片和标签是否配对
    paired_files = []
    for image_file in image_files:
        base_name = os.path.splitext(image_file)[0]
        label_file = base_name + '.txt'
        if label_file in label_files:
            paired_files.append((image_file, label_file))
    return paired_files


# 将文件按比例划分并拷贝到相应目录
def split_and_copy(paired_files, images_path, labels_path, images_dir, labels_dir, train_ratio, val_ratio):
    random.shuffle(paired_files)  # 随机打乱

    total_files = len(paired_files)
    train_count = floor(total_files * train_ratio)
    val_count = floor(total_files * val_ratio)
    test_count = total_files - train_count - val_count

    splits = {
        'train': paired_files[:train_count],
        'val': paired_files[train_count:train_count + val_count],
        'test': paired_files[train_count + val_count:]
    }

    for split, files in splits.items():
        for image_file, label_file in files:
            shutil.copy(os.path.join(images_path, image_file), os.path.join(images_dir, split, image_file))
            shutil.copy(os.path.join(labels_path, label_file), os.path.join(labels_dir, split, label_file))
        print(f'{split}: {len(files)} files')


# 主函数
def main():
    # 写死的路径
    images_path = "E:\\DataSet\\LC\\large_coal_blocked_yolo\\totalImages"  # 替换为实际图片文件夹路径
    labels_path = "E:\\DataSet\\LC\\large_coal_blocked_yolo\\totalLabels"  # 替换为实际txt文件夹路径
    output_dir = "E:\\DataSet\\LC\\large_coal_blocked_yolo\\output"  # 替换为实际输出主目录路径

    # 数据划分比例
    train_ratio = 0.7
    val_ratio = 0.3
    test_ratio = 0

    # 容差值用于浮点数比较
    epsilon = 1e-6

    # 确保比例之和等于1
    assert abs(train_ratio + val_ratio + test_ratio - 1) < epsilon, "比例之和必须等于1"

    # 创建目录
    images_dir, labels_dir = create_dirs(output_dir)

    # 获取文件列表
    paired_files = get_files(images_path, labels_path)

    # 进行划分并拷贝
    split_and_copy(paired_files, images_path, labels_path, images_dir, labels_dir, train_ratio, val_ratio)


# 调用主函数
if __name__ == "__main__":
    main()

2.2 版本2

import os
import shutil
import random

# YOLO格式数据集保存路径
yolo_images_path1 = 'E:\\DataSet\\helmet-VOC'
yolo_labels_path1 = 'E:\\DataSet\\helmet-YOLO'
yolo_data_path = yolo_labels_path1

yolo_images_path = os.path.join(yolo_images_path1, 'JPEGImages')
yolo_labels_path = os.path.join(yolo_labels_path1, 'labels')

# 创建划分后的目录结构
train_images_path = os.path.join(yolo_data_path, 'train', 'images')
train_labels_path = os.path.join(yolo_data_path, 'train', 'labels')
val_images_path = os.path.join(yolo_data_path, 'val', 'images')
val_labels_path = os.path.join(yolo_data_path, 'val', 'labels')
test_images_path = os.path.join(yolo_data_path, 'test', 'images')
test_labels_path = os.path.join(yolo_data_path, 'test', 'labels')

os.makedirs(train_images_path, exist_ok=True)
os.makedirs(train_labels_path, exist_ok=True)
os.makedirs(val_images_path, exist_ok=True)
os.makedirs(val_labels_path, exist_ok=True)
os.makedirs(test_images_path, exist_ok=True)
os.makedirs(test_labels_path, exist_ok=True)

# 获取所有图片文件名（不包含扩展名）
image_files = [f[:-4] for f in os.listdir(yolo_images_path) if f.endswith('.png')]

# 随机打乱文件顺序
random.shuffle(image_files)

# 划分数据集比例
train_ratio = 0.7
val_ratio = 0.2
test_ratio = 0.1

train_count = int(train_ratio * len(image_files))
val_count = int(val_ratio * len(image_files))
test_count = len(image_files) - train_count - val_count

train_files = image_files[:train_count]
val_files = image_files[train_count:train_count + val_count]
test_files = image_files[train_count + val_count:]

# 移动文件到相应的目录
def move_files(files, src_images_path, src_labels_path, dst_images_path, dst_labels_path):
    for file in files:
        src_image_file = os.path.join(src_images_path, f"{file}.png")
        src_label_file = os.path.join(src_labels_path, f"{file}.txt")
        dst_image_file = os.path.join(dst_images_path, f"{file}.png")
        dst_label_file = os.path.join(dst_labels_path, f"{file}.txt")

        if os.path.exists(src_image_file) and os.path.exists(src_label_file):
            shutil.move(src_image_file, dst_image_file)
            shutil.move(src_label_file, dst_label_file)

# 移动训练集文件
move_files(train_files, yolo_images_path, yolo_labels_path, train_images_path, train_labels_path)
# 移动验证集文件
move_files(val_files, yolo_images_path, yolo_labels_path, val_images_path, val_labels_path)
# 移动测试集文件
move_files(test_files, yolo_images_path, yolo_labels_path, test_images_path, test_labels_path)

print("数据集划分完成！")

三、一步到位

如果不想分两步进行格式转换，那么以下脚本结合了以上两步，直接得到最后按比例划分训练、验证、测试的数据集结果。

注意：需要修改 voc_data_path ，yolo_data_path ，class_mapping 以及 ‘.png’ 后缀。

import os
import shutil
import random
import xml.etree.ElementTree as ET
from tqdm import tqdm

# VOC格式数据集路径
voc_data_path = 'E:\\DataSet-VOC'
voc_annotations_path = os.path.join(voc_data_path, 'Annotations')
voc_images_path = os.path.join(voc_data_path, 'JPEGImages')

# YOLO格式数据集保存路径
yolo_data_path = 'E:\\DataSet-YOLO'
yolo_images_path = os.path.join(yolo_data_path, 'images')
yolo_labels_path = os.path.join(yolo_data_path, 'labels')

# 创建YOLO格式数据集目录
os.makedirs(yolo_images_path, exist_ok=True)
os.makedirs(yolo_labels_path, exist_ok=True)

# 类别映射 (可以根据自己的数据集进行调整)
class_mapping = {
    'head': 0,
    'helmet': 1,
    'person': 2,
    # 添加更多类别...
}

def convert_voc_to_yolo(voc_annotation_file, yolo_label_file):
    tree = ET.parse(voc_annotation_file)
    root = tree.getroot()

    size = root.find('size')
    width = float(size.find('width').text)
    height = float(size.find('height').text)

    with open(yolo_label_file, 'w') as f:
        for obj in root.findall('object'):
            cls = obj.find('name').text
            if cls not in class_mapping:
                continue
            cls_id = class_mapping[cls]
            xmlbox = obj.find('bndbox')
            xmin = float(xmlbox.find('xmin').text)
            ymin = float(xmlbox.find('ymin').text)
            xmax = float(xmlbox.find('xmax').text)
            ymax = float(xmlbox.find('ymax').text)

            x_center = (xmin + xmax) / 2.0 / width
            y_center = (ymin + ymax) / 2.0 / height
            w = (xmax - xmin) / width
            h = (ymax - ymin) / height

            f.write(f"{cls_id} {x_center} {y_center} {w} {h}\n")

# 遍历VOC数据集的Annotations目录，进行转换
print("开始VOC到YOLO格式转换...")
for voc_annotation in tqdm(os.listdir(voc_annotations_path)):
    if voc_annotation.endswith('.xml'):
        voc_annotation_file = os.path.join(voc_annotations_path, voc_annotation)
        image_id = os.path.splitext(voc_annotation)[0]
        voc_image_file = os.path.join(voc_images_path, f"{image_id}.png")
        yolo_label_file = os.path.join(yolo_labels_path, f"{image_id}.txt")
        yolo_image_file = os.path.join(yolo_images_path, f"{image_id}.png")

        convert_voc_to_yolo(voc_annotation_file, yolo_label_file)
        if os.path.exists(voc_image_file):
            shutil.copy(voc_image_file, yolo_image_file)

print("VOC到YOLO格式转换完成！")

# 划分数据集
train_images_path = os.path.join(yolo_data_path, 'train', 'images')
train_labels_path = os.path.join(yolo_data_path, 'train', 'labels')
val_images_path = os.path.join(yolo_data_path, 'val', 'images')
val_labels_path = os.path.join(yolo_data_path, 'val', 'labels')
test_images_path = os.path.join(yolo_data_path, 'test', 'images')
test_labels_path = os.path.join(yolo_data_path, 'test', 'labels')

os.makedirs(train_images_path, exist_ok=True)
os.makedirs(train_labels_path, exist_ok=True)
os.makedirs(val_images_path, exist_ok=True)
os.makedirs(val_labels_path, exist_ok=True)
os.makedirs(test_images_path, exist_ok=True)
os.makedirs(test_labels_path, exist_ok=True)

# 获取所有图片文件名（不包含扩展名）
image_files = [f[:-4] for f in os.listdir(yolo_images_path) if f.endswith('.png')]

# 随机打乱文件顺序
random.shuffle(image_files)

# 划分数据集比例
train_ratio = 0.7
val_ratio = 0.2
test_ratio = 0.1

train_count = int(train_ratio * len(image_files))
val_count = int(val_ratio * len(image_files))
test_count = len(image_files) - train_count - val_count

train_files = image_files[:train_count]
val_files = image_files[train_count:train_count + val_count]
test_files = image_files[train_count + val_count:]

# 移动文件到相应的目录
def move_files(files, src_images_path, src_labels_path, dst_images_path, dst_labels_path):
    for file in tqdm(files):
        src_image_file = os.path.join(src_images_path, f"{file}.png")
        src_label_file = os.path.join(src_labels_path, f"{file}.txt")
        dst_image_file = os.path.join(dst_images_path, f"{file}.png")
        dst_label_file = os.path.join(dst_labels_path, f"{file}.txt")

        if os.path.exists(src_image_file) and os.path.exists(src_label_file):
            shutil.move(src_image_file, dst_image_file)
            shutil.move(src_label_file, dst_label_file)

# 移动训练集文件
print("移动训练集文件...")
move_files(train_files, yolo_images_path, yolo_labels_path, train_images_path, train_labels_path)
# 移动验证集文件
print("移动验证集文件...")
move_files(val_files, yolo_images_path, yolo_labels_path, val_images_path, val_labels_path)
# 移动测试集文件
print("移动测试集文件...")
move_files(test_files, yolo_images_path, yolo_labels_path, test_images_path, test_labels_path)

print("数据集划分完成！")

# 删除原始的 images 和 labels 文件夹
shutil.rmtree(yolo_images_path)
shutil.rmtree(yolo_labels_path)

print("原始 images 和 labels 文件夹删除完成！")

版权声明：本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若内容造成侵权/违法违规/事实不符，请联系邮箱：jacktools123@163.com进行投诉反馈，一经查实，立即删除！