记录yolov8_obb训练自己的数据集

一.数据集制作

1.标注软件：roLabelImg

roLabelImg是基于labelImg改进的，是用来标注为VOC格式的数据，但是在labelImg的基础上增加了能够使标注的框进行旋转的功能。

2.数据格式转换

2.1 xml转txt

# 文件名称   ：roxml_to_dota.py
# 功能描述   ：把rolabelimg标注的xml文件转换成dota能识别的xml文件，
#             再转换成dota格式的txt文件
#            把旋转框 cx,cy,w,h,angle，或者矩形框cx,cy,w,h,转换成四点坐标x1,y1,x2,y2,x3,y3,x4,y4
import os
import xml.etree.ElementTree as ET
import math

cls_list=['mouse']
def edit_xml(xml_file, dotaxml_file):
    """
    修改xml文件
    :param xml_file:xml文件的路径
    :return:
    """


    #dxml_file = open(xml_file,encoding='gbk')
    #tree = ET.parse(dxml_file).getroot()

    tree = ET.parse(xml_file)
    objs = tree.findall('object')
    for ix, obj in enumerate(objs):
        x0 = ET.Element("x0")  # 创建节点
        y0 = ET.Element("y0")
        x1 = ET.Element("x1")
        y1 = ET.Element("y1")
        x2 = ET.Element("x2")
        y2 = ET.Element("y2")
        x3 = ET.Element("x3")
        y3 = ET.Element("y3")
        # obj_type = obj.find('bndbox')
        # type = obj_type.text
        # print(xml_file)

        if (obj.find('robndbox') == None):
            obj_bnd = obj.find('bndbox')
            obj_xmin = obj_bnd.find('xmin')
            obj_ymin = obj_bnd.find('ymin')
            obj_xmax = obj_bnd.find('xmax')
            obj_ymax = obj_bnd.find('ymax')
            #以防有负值坐标
            xmin = max(float(obj_xmin.text),0)
            ymin = max(float(obj_ymin.text),0)
            xmax = max(float(obj_xmax.text),0)
            ymax = max(float(obj_ymax.text),0)
            obj_bnd.remove(obj_xmin)  # 删除节点
            obj_bnd.remove(obj_ymin)
            obj_bnd.remove(obj_xmax)
            obj_bnd.remove(obj_ymax)
            x0.text = str(xmin)
            y0.text = str(ymax)
            x1.text = str(xmax)
            y1.text = str(ymax)
            x2.text = str(xmax)
            y2.text = str(ymin)
            x3.text = str(xmin)
            y3.text = str(ymin)
        else:
            obj_bnd = obj.find('robndbox')
            obj_bnd.tag = 'bndbox'  # 修改节点名
            obj_cx = obj_bnd.find('cx')
            obj_cy = obj_bnd.find('cy')
            obj_w = obj_bnd.find('w')
            obj_h = obj_bnd.find('h')
            obj_angle = obj_bnd.find('angle')
            cx = float(obj_cx.text)
            cy = float(obj_cy.text)
            w = float(obj_w.text)
            h = float(obj_h.text)
            angle = float(obj_angle.text)
            obj_bnd.remove(obj_cx)  # 删除节点
            obj_bnd.remove(obj_cy)
            obj_bnd.remove(obj_w)
            obj_bnd.remove(obj_h)
            obj_bnd.remove(obj_angle)

            x0.text, y0.text = rotatePoint(cx, cy, cx - w / 2, cy - h / 2, -angle)
            x1.text, y1.text = rotatePoint(cx, cy, cx + w / 2, cy - h / 2, -angle)
            x2.text, y2.text = rotatePoint(cx, cy, cx + w / 2, cy + h / 2, -angle)
            x3.text, y3.text = rotatePoint(cx, cy, cx - w / 2, cy + h / 2, -angle)


        # obj.remove(obj_type)  # 删除节点
        obj_bnd.append(x0)  # 新增节点
        obj_bnd.append(y0)
        obj_bnd.append(x1)
        obj_bnd.append(y1)
        obj_bnd.append(x2)
        obj_bnd.append(y2)
        obj_bnd.append(x3)
        obj_bnd.append(y3)

        tree.write(dotaxml_file, method='xml', encoding='utf-8')  # 更新xml文件


# 转换成四点坐标
def rotatePoint(xc, yc, xp, yp, theta):
    xoff = xp - xc;
    yoff = yp - yc;
    cosTheta = math.cos(theta)
    sinTheta = math.sin(theta)
    pResx = cosTheta * xoff + sinTheta * yoff
    pResy = - sinTheta * xoff + cosTheta * yoff
    return str(int(xc + pResx)), str(int(yc + pResy))


def totxt(xml_path, out_path):
    # 想要生成的txt文件保存的路径，这里可以自己修改

    files = os.listdir(xml_path)
    i=0
    for file in files:

        tree = ET.parse(xml_path + os.sep + file)
        root = tree.getroot()

        name = file.split('.')[0]

        output = out_path +'\\'+name + '.txt'
        file = open(output, 'w')
        i=i+1
        objs = tree.findall('object')
        for obj in objs:
            cls = obj.find('name').text
            box = obj.find('bndbox')
            x0 = int(float(box.find('x0').text))
            y0 = int(float(box.find('y0').text))
            x1 = int(float(box.find('x1').text))
            y1 = int(float(box.find('y1').text))
            x2 = int(float(box.find('x2').text))
            y2 = int(float(box.find('y2').text))
            x3 = int(float(box.find('x3').text))
            y3 = int(float(box.find('y3').text))
            if x0<0:
                x0=0
            if x1<0:
                x1=0
            if x2<0:
                x2=0
            if x3<0:
                x3=0
            if y0<0:
                y0=0
            if y1<0:
                y1=0
            if y2<0:
                y2=0
            if y3<0:
                y3=0
            for cls_index,cls_name in enumerate(cls_list):
                if cls==cls_name:
                    file.write("{} {} {} {} {} {} {} {} {} {}\n".format(x0, y0, x1, y1, x2, y2, x3, y3, cls,cls_index))
        file.close()
        # print(output)
        print(i)

if __name__ == '__main__':
    # -----**** 第一步：把xml文件统一转换成旋转框的xml文件 ****-----
    roxml_path = 'data_mouse_ro_1/org_xml' 
    dotaxml_path = 'data_mouse_ro_1/dotaxml'  
    out_path = 'data_mouse_ro_1/dotatxt'   
    filelist = os.listdir(roxml_path)
    for file in filelist:
        edit_xml(os.path.join(roxml_path, file), os.path.join(dotaxml_path, file))

    # -----**** 第二步：把旋转框xml文件转换成txt格式 ****-----
    totxt(dotaxml_path, out_path)

2.2 dota_to_yolo_obb

dota数据格式：937.0 913.0 921.0 912.0 923.0 874.0 940.0 875.0 small-vehicle 0

yolo_obb格式：class_index, x1, y1, x2, y2, x3, y3, x4, y4

sys.path.append('/path/to/ultralytics')
from ultralytics.data.converter import convert_dota_to_yolo_obb
convert_dota_to_yolo_obb('/home/fut/project/ultralytics-main/ultralytics/datasets_ro')

跳转到convert_dota_to_yolo_obb.py函数，对class_mapping进行修改

2.3 分割数据集

数据集文件分布格式如下：

datasets
	--images
		--train
		--val
	--labelTxt
		--trian
		--val

分割代码：

import os
import random
import shutil

# 设置随机数种子
random.seed(42)

# 数据集文件夹路径和输出文件夹路径
data_folder = 'data_mouse_ro_1'
img_folder = 'data_mouse_ro_1/dataset/images'
label_folder = 'data_mouse_ro_1/dataset/labels'

# 计算每个子集的大小
total_files = len(os.listdir(os.path.join(data_folder, 'img')))
train_size = int(total_files * 0.9)
test_size = int(total_files - train_size)

# 获取所有图像文件的文件名列表
image_files = os.listdir(os.path.join(data_folder, 'img'))
random.shuffle(image_files)

# 复制图像和标注文件到相应的子集文件夹中
for i, image_file in enumerate(image_files):
    base_file_name = os.path.splitext(image_file)[0]
    image_path = os.path.join(data_folder, 'img', image_file)
    label_path = os.path.join(data_folder, 'dotatxt', base_file_name + '.txt')

    if i < train_size:
        print(image_path)
        #print(os.path.join(img_folder, 'train'))
        shutil.copy(image_path, os.path.join(img_folder, 'train'))
        shutil.copy(label_path, os.path.join(label_folder, 'train_original'))
    else:
        shutil.copy(image_path, os.path.join(img_folder, 'val'))
        shutil.copy(label_path, os.path.join(label_folder, 'val_original'))

二.开始训练

（1）下载预训练权重
（2）创建dota8-obb.yaml，修改相关参数
（3）修改yolov8-obb.yaml参数，修改nc
（4）训练

from ultralytics import YOLO
 
def main():
    model = YOLO('yolov8n-obb.yaml').load('yolov8n-obb.pt')  # build from YAML and transfer weights
    model.train(data='dota8-obb.yaml', epochs=100, imgsz=640, batch=4, workers=4)
if __name__ == '__main__':
    main()

参考：

全网首发！Yolov8_obb旋转框训练、测试、推理手把手教学（DOTA1.0数据集map50已达80%）

Yolov8_obb（prob loss) 基于anchor_free的旋转框目标检测，剪枝，跟踪（ByteTracker）

YOLOv8-OBB推理详解及部署实现

roLabelImg的使用

关于旋转框定义的一些理解和感想

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。如若转载，请注明出处：/a/349992.html

如若内容造成侵权/违法违规/事实不符，请联系我们进行投诉反馈qq邮箱809451989@qq.com，一经查实，立即删除！