问题描述

准备使用yolov5训练自己的模型，自己将下载的开源数据集按照自己的要求重新标注了一下，然后现在对其进行划分。

问题分析

划分数据集主要的步骤就是，首先要将数据集打乱顺序，然后按照一定的比例将其分为训练集，验证集和测试集。
这里我定的比例是7：1：2。

步骤流程

1、将数据集打乱顺序

数据集有图片和标注文件，我们需要把两种文件绑定然后将其打乱顺序。
首先读取数据后，将两种文件通过zip函数绑定

	each_class_image = []
    each_class_label = []
    for image in os.listdir(file_path):
        each_class_image.append(image)
    for label in os.listdir(xml_path):
        each_class_label.append(label)
    data=list(zip(each_class_image,each_class_label))

然后打乱顺序，再将两个列表分开

    random.shuffle(data)
    each_class_image,each_class_label=zip(*data)

2、按照确定好的比例将两个列表元素分割

分别用三个列表储存一下图片和标注文件的元素

	train_images = each_class_image[0:int(train_rate * total)]
    val_images = each_class_image[int(train_rate * total):int((train_rate + val_rate) * total)]
    test_images = each_class_image[int((train_rate + val_rate) * total):]
    
    train_labels = each_class_label[0:int(train_rate * total)]
    val_labels = each_class_label[int(train_rate * total):int((train_rate + val_rate) * total)]
    test_labels = each_class_label[int((train_rate + val_rate) * total):]

3、在本地生成文件夹，将划分好的数据集分别保存

这样就保存好了。

    for image in train_images:
        #print(image)
        old_path = file_path + '/' + image
        new_path1 = new_file_path + '/' + 'train' + '/' + 'images'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)

    for label in train_labels:
        #print(label)
        old_path = xml_path + '/' + label
        new_path1 = new_file_path + '/' + 'train' + '/' + 'labels'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)

    for image in val_images:
        old_path = file_path + '/' + image
        new_path1 = new_file_path + '/' + 'val' + '/' + 'images'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)

    for label in val_labels:
        old_path = xml_path + '/' + label
        new_path1 = new_file_path + '/' + 'val' + '/' + 'labels'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)

    for image in test_images:
        old_path = file_path + '/' + image
        new_path1 = new_file_path + '/' + 'test' + '/' + 'images'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)

    for label in test_labels:
        old_path = xml_path + '/' + label
        new_path1 = new_file_path + '/' + 'test' + '/' + 'labels'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)

运行结果展示

直接运行单个python文件即可。

运行完毕
去本地查看




图片和标注文件乱序，且一一对应。

完整代码分享

import os
import shutil
import random

random.seed(0)


def split_data(file_path,xml_path, new_file_path, train_rate, val_rate, test_rate):
    each_class_image = []
    each_class_label = []
    for image in os.listdir(file_path):
        each_class_image.append(image)
    for label in os.listdir(xml_path):
        each_class_label.append(label)
    data=list(zip(each_class_image,each_class_label))
    total = len(each_class_image)
    random.shuffle(data)
    each_class_image,each_class_label=zip(*data)
    train_images = each_class_image[0:int(train_rate * total)]
    val_images = each_class_image[int(train_rate * total):int((train_rate + val_rate) * total)]
    test_images = each_class_image[int((train_rate + val_rate) * total):]
    train_labels = each_class_label[0:int(train_rate * total)]
    val_labels = each_class_label[int(train_rate * total):int((train_rate + val_rate) * total)]
    test_labels = each_class_label[int((train_rate + val_rate) * total):]

    for image in train_images:
        print(image)
        old_path = file_path + '/' + image
        new_path1 = new_file_path + '/' + 'train' + '/' + 'images'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)

    for label in train_labels:
        print(label)
        old_path = xml_path + '/' + label
        new_path1 = new_file_path + '/' + 'train' + '/' + 'labels'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)

    for image in val_images:
        old_path = file_path + '/' + image
        new_path1 = new_file_path + '/' + 'val' + '/' + 'images'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)

    for label in val_labels:
        old_path = xml_path + '/' + label
        new_path1 = new_file_path + '/' + 'val' + '/' + 'labels'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)

    for image in test_images:
        old_path = file_path + '/' + image
        new_path1 = new_file_path + '/' + 'test' + '/' + 'images'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + image
        shutil.copy(old_path, new_path)

    for label in test_labels:
        old_path = xml_path + '/' + label
        new_path1 = new_file_path + '/' + 'test' + '/' + 'labels'
        if not os.path.exists(new_path1):
            os.makedirs(new_path1)
        new_path = new_path1 + '/' + label
        shutil.copy(old_path, new_path)


if __name__ == '__main__':
    file_path = "D:/Files/dataSet/drone_images"
    xml_path = 'D:/Files/dataSet/drone_labels'
    new_file_path = "D:/Files/dataSet/droneData"
    split_data(file_path,xml_path, new_file_path, train_rate=0.7, val_rate=0.1, test_rate=0.2)