yolov7--制作自己的数据集（VOC转YOLO）

1. 数据集的制作

1.1 labelimg安装

​ 1.1.1 创建虚拟环境

​ 学习计算机视觉，标注工具会与你形影不离，因此我建议将其安装在独立的环境中，便于查找。

# 查看当前已有的虚拟环境
conda env list
# 创建
conda create - n env_name python=x.x   # env_name: 虚拟环境的名称  python=...:指定python的版本
#激活虚拟环境
conda activate env_name

1.1.2 激活虚拟环境

所示的就是我创建的虚拟环境啦：

​ 1.1.3 安装 labelimg

pip install labelimg -i https://pypi.tuna.tsinghua.edu.cn/simple

1.2 labelimg的使用

​ 1.2.1 使用

1. 在刚才创建的虚拟环境中输入labelimg —>回车–>弹出界面
   

1.2.1 文件夹的创建

​ 1.2.2 工具的使用

​ 1.2.2.1 文件夹对应

​ 1.2.2.2 标注

2. 数据集转换，VOC转换成YOLO格式

2.1 xml 文件转换成txt格式

​ 代码测试过了,直接复制用就好了

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

#1. 将这个地方改成自己类别的列表
class_names = ['plate']
# 2. 将路径修改
xmlpath = r'.....'  # 原xml路径
txtpath = r'......'  # 转换后txt文件存放路径


files = []
if not os.path.exists(txtpath):
    os.makedirs(txtpath)
 
for root, dirs, files in os.walk(xmlpath):
    None
 
number = len(files)
print(number)
i = 0
while i < number:
 
    name = files[i][0:-4]
    xml_name = name + ".xml"
    txt_name = name + ".txt"
    xml_file_name = xmlpath + xml_name
    txt_file_name = txtpath + txt_name
 
    xml_file = open(xml_file_name)
    tree = ET.parse(xml_file)
    root = tree.getroot()
    # filename = root.find('name').text
 
    # image_name = root.find('filename').text
    w = int(root.find('size').find('width').text)
    h = int(root.find('size').find('height').text)
 
    f_txt = open(txt_file_name, 'w+')
    content = ""
 
    first = True
 
    for obj in root.iter('object'):
 
        name = obj.find('name').text
        class_num = class_names.index(name)
        # class_num = 0
 
        xmlbox = obj.find('bndbox')
 
        x1 = int(xmlbox.find('xmin').text)
        x2 = int(xmlbox.find('xmax').text)
        y1 = int(xmlbox.find('ymin').text)
        y2 = int(xmlbox.find('ymax').text)
 
        if first:
            content += str(class_num) + " " + \
                       str((x1 + x2) / 2 / w) + " " + str((y1 + y2) / 2 / h) + " " + \
                       str((x2 - x1) / w) + " " + str((y2 - y1) / h)
            first = False
        else:
            content += "\n" + \
                       str(class_num) + " " + \
                       str((x1 + x2) / 2 / w) + " " + str((y1 + y2) / 2 / h) + " " + \
                       str((x2 - x1) / w) + " " + str((y2 - y1) / h)
 
    # print(str(i / (number - 1) * 100) + "%\n")
    print(content)
    f_txt.write(content)
    f_txt.close()
    xml_file.close()
    i += 1

2.2 train与val的划分

1. 修改路径
2. 修改训练/验证集的比例

 
import os
import random 
random.seed(0)
# 1. 将路径修改为自己的
xmlfilepath=r'E:\yolov7-main\VOC2007\Annotations'
saveBasePath=r'E:\yolov7-main\VOC2007\ImageSets\Main/'
 
#----------------------------------------------------------------------#
#   想要增加测试集修改trainval_percent
#   train_percent不需要修改
#----------------------------------------------------------------------#
trainval_percent = 1
train_percent = 0.8
 
temp_xml = os.listdir(xmlfilepath)
total_xml = []
for xml in temp_xml:
    if xml.endswith(".xml"):
        total_xml.append(xml)
 
num=len(total_xml)  
list=range(num)  
tv=int(num*trainval_percent)  
tr=int(tv*train_percent)  
trainval= random.sample(list,tv)  
train=random.sample(trainval,tr)  
 
print("train and val size",tv)
print("traub suze",tr)
ftrainval = open(os.path.join(saveBasePath,'trainval.txt'), 'w')  
ftest = open(os.path.join(saveBasePath,'test.txt'), 'w')  
ftrain = open(os.path.join(saveBasePath,'train.txt'), 'w')  
fval = open(os.path.join(saveBasePath,'val.txt'), 'w')  
 
for i  in list:  
    name=total_xml[i][:-4]+'\n'  
    if i in trainval:  
        ftrainval.write(name)  
        if i in train:  
            ftrain.write(name)  
        else:  
            fval.write(name)  
    else:  
        ftest.write(name)  
  
ftrainval.close()  
ftrain.close()  
fval.close()  
ftest .close()

2.3 复制出图片和标签

​ 按照train.txt,val.txt，将图片和txt文件，分别复制到labels和images中
1 . 路径名称
2. .jpg 或者.png 修改成自己对应的就可以了

import os
import shutil
from tqdm import tqdm
 
SPLIT_PATH = r"E:\yolov7-main\VOC2007\ImageSets\Main"
IMGS_PATH = r"E:\yolov7-main\VOC2007\JPEGImages"
TXTS_PATH = r"E:\yolov7-main\VOC2007\txts"
 
TO_IMGS_PATH = r'E:\yolov7-main\yolov7-main\lesion\images'
TO_TXTS_PATH =r'E:\yolov7-main\yolov7-main\lesion\labels'
 
data_split = ['train.txt', 'val.txt']
to_split = ['train2007', 'val2007']
 
for index, split in enumerate(data_split):
    split_path = os.path.join(SPLIT_PATH, split)
 
    to_imgs_path = os.path.join(TO_IMGS_PATH, to_split[index])
    if not os.path.exists(to_imgs_path):
        os.makedirs(to_imgs_path)
 
    to_txts_path = os.path.join(TO_TXTS_PATH, to_split[index])
    if not os.path.exists(to_txts_path):
        os.makedirs(to_txts_path)
 
    f = open(split_path, 'r')
    count = 1
 
    for line in tqdm(f.readlines(), desc="{} is copying".format(to_split[index])):
        # 复制图片
        src_img_path = os.path.join(IMGS_PATH, line.strip() + '.png')
        dst_img_path = os.path.join(to_imgs_path, line.strip() + '.png')
        if os.path.exists(src_img_path):
            shutil.copyfile(src_img_path, dst_img_path)
        else:
            print("error file: {}".format(src_img_path))
 
        # 复制txt标注文件
        src_txt_path = os.path.join(TXTS_PATH, line.strip() + '.txt')
        dst_txt_path = os.path.join(to_txts_path, line.strip() + '.txt')
        if os.path.exists(src_txt_path):
            shutil.copyfile(src_txt_path, dst_txt_path)
        else:
            print("error file: {}".format(src_txt_path))

2.4 文件夹排布