将dior r 数据集标签转换为dota格式标签

最新推荐文章于 2024-01-26 15:20:58 发布

beneficial

最新推荐文章于 2024-01-26 15:20:58 发布

阅读量231

点赞数 2

文章标签：目标检测人工智能计算机视觉

本文链接：https://blog.csdn.net/beneficial/article/details/133345157

版权

将dior r 数据集标签转换为dota格式标签

时间：2023.9.27

1.将dior数据集标签转换为dota格式标签

import os
import xml.etree.ElementTree as ET

# 输入文件夹路径和输出文件夹路径
input_folder = '/root/autodl-tmp/dior/Annotations/Oriented Bounding Boxes/'
output_folder = '/root/autodl-tmp/dior_dota_format/all_annfiles/'


# 遍历输入文件夹中的所有XML文件
for filename in os.listdir(input_folder):
    if filename.endswith('.xml'):
        xml_path = os.path.join(input_folder, filename)
        print(f'convert {filename}')

        # 解析XML文件
        tree = ET.parse(xml_path)
        root = tree.getroot()

        # 创建用于存储文本数据的列表
        text_data = []

        # 遍历XML元素并提取所需的信息
        for obj in root.findall('.//object'):
            robndbox = obj.find('robndbox')
            if robndbox is not None:
                x_left_top = robndbox.find('x_left_top').text
                y_left_top = robndbox.find('y_left_top').text
                x_right_top = robndbox.find('x_right_top').text
                y_right_top = robndbox.find('y_right_top').text
                x_right_bottom = robndbox.find('x_right_bottom').text
                y_right_bottom = robndbox.find('y_right_bottom').text
                x_left_bottom = robndbox.find('x_left_bottom').text
                y_left_bottom = robndbox.find('y_left_bottom').text
                name = obj.find('name').text
                difficult = obj.find('difficult').text

                # 将提取的信息格式化并添加到文本数据列表中
                text_line = f"{x_left_top} {y_left_top} {x_right_top} {y_right_top} {x_right_bottom} {y_right_bottom} {x_left_bottom} {y_left_bottom} {name} {difficult}\n"
                text_data.append(text_line)

        # 创建输出文件路径
        output_path = os.path.join(output_folder, filename.replace('.xml', '.txt'))

        # 将文本数据写入输出文件
        with open(output_path, 'w') as output_file:
            output_file.writelines(text_data)

print("转换完成！")

trainval和test共23463个标签文件

2.将trainval和test标签文件分开

import os
import shutil

# 源文件夹和目标文件夹路径
source_folder = '/root/autodl-tmp/dior_dota_format/all_annfiles/'
trainval_target_folder = '/root/autodl-tmp/dior_dota_format/trainval/annfiles/'

# 读取trainval.txt文件中的文件名列表
with open('/root/autodl-tmp/dior/ImageSets/Main/trainval.txt', 'r') as file:
    file_names = file.read().splitlines()

# 遍历文件名列表并复制文件
total_trainval = 0
for file_name in file_names:
    source_file_path = os.path.join(source_folder, f"{file_name}.txt")
    target_file_path = os.path.join(trainval_target_folder, f"{file_name}.txt")

    # 使用shutil库进行文件复制
    if os.path.exists(source_file_path):
        total_trainval += 1
        shutil.copy(source_file_path, target_file_path)
        print(f"复制 {file_name}.txt 完成")
print("trainval 复制完成！")
print(f"total trainval {total_trainval}")


test_target_folder = '/root/autodl-tmp/dior_dota_format/test/annfiles/'
# 读取trainval.txt文件中的文件名列表
with open('/root/autodl-tmp/dior/ImageSets/Main/test.txt', 'r') as file:
    file_names = file.read().splitlines()

# 遍历文件名列表并复制文件
total_test = 0
for file_name in file_names:
    source_file_path = os.path.join(source_folder, f"{file_name}.txt")
    target_file_path = os.path.join(test_target_folder, f"{file_name}.txt")

    # 使用shutil库进行文件复制
    if os.path.exists(source_file_path):
        total_test += 1
        shutil.copy(source_file_path, target_file_path)
        print(f"复制 {file_name}.txt 完成")

print("test 复制完成！")
print(f"total test {total_test}")

print(f"total trainval {total_trainval}")
print(f"total test {total_test}")