【YOLO】常用脚本

目录

VOC转YOLO

python 复制代码
import os
import xml.etree.ElementTree as ET


def convert(size, box):
    dw = 1. / size[0]
    dh = 1. / size[1]
    x = (box[0] + box[1]) / 2.0
    y = (box[2] + box[3]) / 2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)


def convert_annotation(xml_file, output_dir, labels):
    # 加载XML文件
    tree = ET.parse(xml_file)
    root = tree.getroot()

    # 获取图像尺寸
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    # 初始化YOLO格式的标注字符串
    result_str = ""

    # 遍历所有对象
    for obj in root.iter('object'):
        difficult = obj.find('difficult')
        if difficult is not None:
            difficult = difficult.text
            if int(difficult) == 1:
                continue
        cls = obj.find('name').text
        if cls not in labels:
            continue
        cls_id = labels.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)
        result_str = result_str + " " + " ".join([str(a) for a in bb]) + " " + str(cls_id)

        # 写入YOLO格式的标注文件
    file_name = os.path.splitext(os.path.basename(xml_file))[0]
    with open(os.path.join(output_dir, file_name + ".txt"), "w") as f:
        f.write(result_str.strip())


def main(voc_dir, output_dir, labels):
    # 遍历Annotations文件夹
    annotations_dir = os.path.join(voc_dir, "Annotations")
    for xml_file in os.listdir(annotations_dir):
        if xml_file.endswith(".xml"):
            xml_path = os.path.join(annotations_dir, xml_file)
            convert_annotation(xml_path, output_dir, labels)


if __name__ == "__main__":
	# VOC数据集根目录包含Annotations、JPEGImages等
    voc_dir = "path_to_your_voc_dataset"  
    # 存放转换后的YOLO格式标注文件
    output_dir = "path_to_your_yolo_annotations"
    # 数据集包含类别  
    labels = ['nodule']
    main(voc_dir, output_dir, labels)

划分训练集、测试集与验证集

python 复制代码
import os
import random
from shutil import copyfile


def split_dataset(image_folder, txt_folder, output_folder, split_ratio=(0.8, 0.1, 0.1)):
    # Ensure output folders exist
    for dataset in ['train', 'val', 'test']:
        if not os.path.exists(os.path.join(output_folder, dataset, 'images')):
            os.makedirs(os.path.join(output_folder, dataset, 'images'))
        if not os.path.exists(os.path.join(output_folder, dataset, 'labels')):
            os.makedirs(os.path.join(output_folder, dataset, 'labels'))

    # Get list of image files
    image_files = [f for f in os.listdir(image_folder) if f.endswith(('.jpg', '.jpeg', '.png'))]
    random.shuffle(image_files)

    num_images = len(image_files)
    num_train = int(split_ratio[0] * num_images)
    num_val = int(split_ratio[1] * num_images)

    train_images = image_files[:num_train]
    val_images = image_files[num_train:num_train + num_val]
    test_images = image_files[num_train + num_val:]

    # Copy images to respective folders
    for dataset, images_list in zip(['train', 'val', 'test'], [train_images, val_images, test_images]):
        for image_file in images_list:
            image_path = os.path.join(image_folder, image_file)
            copyfile(image_path, os.path.join(output_folder, dataset, 'images', image_file))
            txt_file = os.path.splitext(image_file)[0] + '.txt'
            txt_path = os.path.join(txt_folder, txt_file)

            # Copy corresponding txt file if exists
            if os.path.exists(txt_path):
                copyfile(txt_path, os.path.join(output_folder, dataset, 'labels', txt_file))


if __name__ == "__main__":
	# 图片路径
    image_folder_path = "./JPEGImages"
    # 标签路径
    txt_folder_path = "./Labels"
    # 划分后数据集路径
    output_dataset_path = "./dataset"

    split_dataset(image_folder_path, txt_folder_path, output_dataset_path)
相关推荐
hunter2062063 分钟前
用opencv生成视频流,然后用rtsp进行拉流显示
人工智能·python·opencv
Daphnis_z4 分钟前
大模型应用编排工具Dify之常用编排组件
人工智能·chatgpt·prompt
yuanbenshidiaos1 小时前
【大数据】机器学习----------强化学习机器学习阶段尾声
人工智能·机器学习
盼小辉丶6 小时前
TensorFlow深度学习实战——情感分析模型
深度学习·神经网络·tensorflow
好评笔记6 小时前
AIGC视频生成模型:Stability AI的SVD(Stable Video Diffusion)模型
论文阅读·人工智能·深度学习·机器学习·计算机视觉·面试·aigc
算家云6 小时前
TangoFlux 本地部署实用教程:开启无限音频创意脑洞
人工智能·aigc·模型搭建·算家云、·应用社区·tangoflux
AI街潜水的八角7 小时前
工业缺陷检测实战——基于深度学习YOLOv10神经网络PCB缺陷检测系统
pytorch·深度学习·yolo
叫我:松哥8 小时前
基于Python django的音乐用户偏好分析及可视化系统设计与实现
人工智能·后端·python·mysql·数据分析·django
熊文豪9 小时前
深入解析人工智能中的协同过滤算法及其在推荐系统中的应用与优化
人工智能·算法
Vol火山9 小时前
AI引领工业制造智能化革命:机器视觉与时序数据预测的双重驱动
人工智能·制造