旋转目标检测-环境配置-数据集制作_旋转目标检测数据集

一、环境配置

• Ubuntu 22.04
• Torch 1.10
• CUDA 11.3
• python 3.9

      环境配置参考下面链接（建议Linux系统）yolov5_obb/install.md at master · hukaixuan19970627/yolov5_obb (github.com)https://github.com/hukaixuan19970627/yolov5_obb/blob/master/docs/install.md

•  创建虚拟环境

conda create -n Py39_Torch1.10_cu11.3 python=3.9 -y 
source activate Py39_Torch1.10_cu11.3

•  查看CUDA版本（确保CUDA runtime api version ≤ CUDA driver version）

nvcc -V
nvidia-smi

•  安装PyTorch和torchvision

pip3 install torch==1.10.1+cu113 torchvision==0.11.2+cu113 torchaudio==0.10.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
nvcc -V
python
>>> import torch
>>> torch.version.cuda
>>> exit()

•  克隆yolov7-obb项目（也可直接在GitHub上下载）

git clone https://github.com/Egrt/yolov7-obb.git

•  配置yolov7-obb所需环境

cd yolov7-obb
pip install -r requirements.txt
cd utils/nms_rotated
python setup.py develop #安装非极大值抑制库

运行 python setup.py develop时报错

可以看出时gcc版本问题，检测已有版本发现gcc 12 > gcc 11

故安装低版本的gcc，并创建软链接（此处要对应改为自己的位置）

sudo apt-get install gcc-10
sudo apt-get install g++-10
 
sudo ln -s /usr/bin/gcc-10 /usr/local/cuda-11.6/bin/gcc #创建软链接

再次运行 python setup.py develop

至此，环境配置完成！！！

二、数据集制作

• 下载官方源码

https://github.com/cgvict/roLabelImg

•  进入下载好的roLabellmg-master文件夹内 ，在终端打开

pyrcc5 -oresources.py resources.qrc
python roLabelImg.py

•  快捷键

•  标注的XML格式

<annotation verified="yes">
  <folder>hsrc</folder>
  <filename>100000001</filename>
  <path>/Users/haoyou/Library/Mobile Documents/com~apple~CloudDocs/OneDrive/hsrc/100000001.bmp</path>
  <source>
    <database>Unknown</database>
  </source>
  <size>
    <width>1166</width>
    <height>753</height>
    <depth>3</depth>
  </size>
  <segmented>0</segmented>
  <object>
    <type>bndbox</type>
    <name>ship</name>
    <pose>Unspecified</pose>
    <truncated>0</truncated>
    <difficult>0</difficult>
    <bndbox>
      <xmin>178</xmin>
      <ymin>246</ymin>
      <xmax>974</xmax>
      <ymax>504</ymax>
    </bndbox>
  </object>
</annotation>

•  数据集格式转换（把旋转框 cx,cy,w,h,angle，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
 
def edit_xml(xml_file, dotaxml_file):
    """
    修改xml文件
    :param xml_file:xml文件的路径
    :return:
    """
    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')
            xmin = float(obj_xmin.text)
            ymin = float(obj_ymin.text)
            xmax = float(obj_xmax.text)
            ymax = float(obj_ymax.text)
            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)
    for file in files:
 
        tree = ET.parse(xml_path + os.sep + file)
        root = tree.getroot()
 
        name = file.strip('.xml')
        output = out_path + name + '.txt'
        file = open(output, 'w')
 
        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))
            file.write("{} {} {} {} {} {} {} {} {} 0\n".format(x0, y0, x1, y1, x2, y2, x3, y3, cls))
        file.close()
        print(output)
 
 
if __name__ == '__main__':
    # -----**** 第一步：把xml文件统一转换成旋转框的xml文件 ****-----
    roxml_path = "./datasets/Annotations"  # 目录下保存的是需要转换的xml文件
    dotaxml_path = './datasets/dotaxml'
    filelist = os.listdir(roxml_path)
    for file in filelist:
        edit_xml(os.path.join(roxml_path, file), os.path.join(dotaxml_path, file))

三、训练自己的数据集

      本文参考yolov7-obb项目如下Egrt/yolov7-obb: 在YOLOv7的基础上使用KLD损失修改为旋转目标检测yolov7-obb (github.com)https://github.com/Egrt/yolov7-obb

• 数据集格式 （其中Annotations为上面格式转换过的xml文件）

VOCdevkit/VOC2007
    ├── Annotations
            ├── 0001.xml
            ├── 0002.xml
                 .
                 .
 
    ├── ImageSets
            ├── Main
 
    ├── JPEGImages
            ├── 0001.xml
            ├── 0002.xml
                 .
                 .

•  运行voc_annotation.py文件，生成2007_train.txt和2007_val.txt文件

•  开始训练