YOLOV5竞赛总结_如何在yolo比赛中获得好的成绩-CSDN博客

本文链接：https://blog.csdn.net/asszyq/article/details/121073544

YOLOV5竞赛总结

这是对最近的比赛使用的YOLOV5进行目标检测的一个总结，主要完成以下工作：
1.对比赛提供的数据集进行数据增强。
2.利用labelimg对数据进行标注。
3.完成图片数据集到VOC数据集的转换。
4.将带有英文标签的VOC数据集转换成中文标签的数据集。
5.数据集格式的转化以及训练集和验证集的划分。
6.YOLOV5显示中文框。
7.利用YOLOV5训练自己的目标检测模型。

利用labelimg制作目标检测数据集

Labelimg是一款开源的数据标注工具，可以标注三种格式：VOC,YOLO,JSON。
从GitHub上下载源码 labelimg下载地址，下载三个主要依赖库PyQt5，PyQt5_tools，lxml，安装完成后，进入到相对应的文件夹下，输入pyrcc5 -o resources.py resources.qrc，如下：
在这里插入图片描述将命令生成的resources.py文件，复制到libs文件夹下，然后利用pycharm打开labelimg项目，运行labelImg.py，就可以打开标注软件，进行数据标注。具体参考文章：labelimg避雷，如何使用labelimg进行标注主要看文章的2.1部分。代码保存在labelImg-master_step1文件夹内。

英文标签的VOC数据集转换成中文标签

此部分为比赛要求，如果没有对目标检测进行中文标注的要求，可以跳过此步骤。
自己制作中文标签的数据集的话：

利用labelimg这个工具标注数据集的时候，直接标为中文即可。标注参考上一部分如何使用labelimg打标签。
如果拿到手的是英文标注的voc数据，则需要进行如下代码转换

# encoding:utf-8
import os
import xml.etree.ElementTree as ET

count = 0
list_xml = []
dict = {
        "red light":"红灯"
        ,"green light":"绿灯"
        ,"yellow light":"黄灯"
        ,"straight red light":"直行红灯"
        ,"straight green light":"直行绿灯"
        ,"straight yellow light":"直行黄灯"
        ,"left turn red light":"左转红灯"
        ,"left turn green light":"左转绿灯"
        ,"left turn yellow light":"左转黄灯"
        }
#这部分，将所有的英文标签和中文标签全部输入进去。
openPath = "VOCdevkit\VOC2007\Annotations"
savePath = "VOCdevkit\VOC2007\Annotations1"
fileList = os.listdir(openPath)  # 得到进程当前工作目录中的所有文件名称列表
for fileName in fileList:  # 获取文件列表中的文件
    if fileName.endswith(".xml"):  # 只看xml文件
        print("filename=:", fileName)
        tree = ET.parse(os.path.join(openPath, fileName))
        root = tree.getroot()
        print("root-tag=:", root.tag)  # ',root-attrib:', root.attrib, ',root-text:', root.text)
        for child in root:  # 第一层解析
            if child.tag == "object":  # 找到object标签
                print(child.tag)
                for sub in child:
                    if sub.tag == "name":
                        print("标签名字:", sub.tag, ";文本内容:", sub.text)
                        if sub.text not in list_xml:
                            list_xml.append(sub.text)
                        if sub.text in list(dict.keys()):
                            sub.text = dict[sub.text]
                            print(sub.text)
                            count = count + 1
        tree.write(os.path.join(savePath, fileName), encoding='utf-8')
    print("=" * 20)

print(count)
for i in list_xml:
    print(i)

主要参考文章的第一部分，具体代码放置在step2文件夹中。

数据集格式的转化以及训练集和验证集的划分

此部分主要实现数据集voc格式到yolo格式的转换，以及训练集和验证集的划分。

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
from shutil import copyfile

classes = ["红灯"
        ,"绿灯"
        ,"黄灯"
        ,"直行红灯"
        ,"直行绿灯"
        ,"直行黄灯"
        ,"左转红灯"
        ,"左转绿灯"
        ,"左转黄灯"
]
# classes=["ball"]

TRAIN_RATIO = 80


def clear_hidden_files(path):
    dir_list = os.listdir(path)
    for i in dir_list:
        abspath = os.path.join(os.path.abspath(path), i)
        if os.path.isfile(abspath):
            if i.startswith("._"):
                os.remove(abspath)
        else:
            clear_hidden_files(abspath)


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(image_id):
    in_file = open('VOCdevkit/VOC2007/Annotations/%s.xml' % image_id,encoding='UTF-8')
    out_file = open('VOCdevkit/VOC2007/YOLOLabels/%s.txt' % image_id, 'w',encoding='UTF-8')
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_id = classes.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)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
    in_file.close()
    out_file.close()


wd = os.getcwd()
wd = os.getcwd()
data_base_dir = os.path.join(wd, "VOCdevkit/")
if not os.path.isdir(data_base_dir):
    os.mkdir(data_base_dir)
work_sapce_dir = os.path.join(data_base_dir, "VOC2007/")
if not os.path.isdir(work_sapce_dir):
    os.mkdir(work_sapce_dir)
annotation_dir = os.path.join(work_sapce_dir, "Annotations/")
if not os.path.isdir(annotation_dir):
    os.mkdir(annotation_dir)
clear_hidden_files(annotation_dir)
image_dir = os.path.join(work_sapce_dir, "JPEGImages/")
if not os.path.isdir(image_dir):
    os.mkdir(image_dir)
clear_hidden_files(image_dir)
yolo_labels_dir = os.path.join(work_sapce_dir, "YOLOLabels/")
if not os.path.isdir(yolo_labels_dir):
    os.mkdir(yolo_labels_dir)
clear_hidden_files(yolo_labels_dir)
yolov5_images_dir = os.path.join(data_base_dir, "images/")
if not os.path.isdir(yolov5_images_dir):
    os.mkdir(yolov5_images_dir)
clear_hidden_files(yolov5_images_dir)
yolov5_labels_dir = os.path.join(data_base_dir, "labels/")
if not os.path.isdir(yolov5_labels_dir):
    os.mkdir(yolov5_labels_dir)
clear_hidden_files(yolov5_labels_dir)
yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/")
if not os.path.isdir(yolov5_images_train_dir):
    os.mkdir(yolov5_images_train_dir)
clear_hidden_files(yolov5_images_train_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, "val/")
if not os.path.isdir(yolov5_images_test_dir):
    os.mkdir(yolov5_images_test_dir)
clear_hidden_files(yolov5_images_test_dir)
yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/")
if not os.path.isdir(yolov5_labels_train_dir):
    os.mkdir(yolov5_labels_train_dir)
clear_hidden_files(yolov5_labels_train_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "val/")
if not os.path.isdir(yolov5_labels_test_dir):
    os.mkdir(yolov5_labels_test_dir)
clear_hidden_files(yolov5_labels_test_dir)

train_file = open(os.path.join(wd, "yolov5_train.txt"), 'w')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'w')
train_file.close()
test_file.close()
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'a')
list_imgs = os.listdir(image_dir)  # list image files
prob = random.randint(1, 100)
print("Probability: %d" % prob)
for i in range(0, len(list_imgs)):
    path = os.path.join(image_dir, list_imgs[i])
    if os.path.isfile(path):
        image_path = image_dir + list_imgs[i]
        voc_path = list_imgs[i]
        (nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path))
        (voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path))
        annotation_name = nameWithoutExtention + '.xml'
        annotation_path = os.path.join(annotation_dir, annotation_name)
        label_name = nameWithoutExtention + '.txt'
        label_path = os.path.join(yolo_labels_dir, label_name)
    prob = random.randint(1, 100)
    print("Probability: %d" % prob)
    if (prob < TRAIN_RATIO):  # train dataset
        if os.path.exists(annotation_path):
            train_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention)  # convert label
            copyfile(image_path, yolov5_images_train_dir + voc_path)
            copyfile(label_path, yolov5_labels_train_dir + label_name)
    else:  # test dataset
        if os.path.exists(annotation_path):
            test_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention)  # convert label
            copyfile(image_path, yolov5_images_test_dir + voc_path)
            copyfile(label_path, yolov5_labels_test_dir + label_name)
train_file.close()
test_file.close()