python划分训练集、验证集和测试集

将图片和标注文件分别划分到文件夹中去

# 将图片和标注数据按比例切分为 训练集和测试集、验证集
import shutil
import random
import os

# 原始路径
image_original_path = 'a/images/'
label_original_path = 'a/annotations/'
# 训练集路径
train_image_path = 'a/train/images/'
train_label_path = 'a/train/labels/'
# 验证集路径
val_image_path = 'a/val/images/'
val_label_path = 'a/val/labels/'
# 测试集路径
test_image_path = 'a/test/images/'
test_label_path = 'a/test/labels/'

# 数据集划分比例，训练集80%，验证集10%，测试集10%
train_percent = 0.8
val_percent = 0.1
test_percent = 0.1

# 检查文件夹是否存在
def mkdir():
    if not os.path.exists(train_image_path):
        os.makedirs(train_image_path)
    if not os.path.exists(train_label_path):
        os.makedirs(train_label_path)

    if not os.path.exists(val_image_path):
        os.makedirs(val_image_path)
    if not os.path.exists(val_label_path):
        os.makedirs(val_label_path)

    if not os.path.exists(test_image_path):
        os.makedirs(test_image_path)
    if not os.path.exists(test_label_path):
        os.makedirs(test_label_path)


def main():
    mkdir()

    total_txt = os.listdir(label_original_path)
    num_txt = len(total_txt)
    list_all_txt = range(num_txt)  # 范围 range(0, num)

    num_train = int(num_txt * train_percent)
    num_val = int(num_txt * val_percent)
    num_test = num_txt - num_train - num_val

    train = random.sample(list_all_txt, num_train)
    # train从list_all_txt取出num_train个元素
    # 所以list_all_txt列表只剩下了这些元素：val_test
    val_test = [i for i in list_all_txt if not i in train]
    # 再从val_test取出num_val个元素，val_test剩下的元素就是test
    val = random.sample(val_test, num_val)
    # 检查两个列表元素是否有重合的元素
    # set_c = set(val_test) & set(val)
    # list_c = list(set_c)
    # print(list_c)
    # print(len(list_c))

    print("训练集数目：{}, 验证集数目：{},测试集数目：{}".format(len(train), len(val), len(val_test) - len(val)))
    for i in list_all_txt:
        name = total_txt[i][:-4]

        srcImage = image_original_path + name + '.jpg'
        srcLabel = label_original_path + name + '.txt'

        if i in train:
            dst_train_Image = train_image_path + name + '.jpg'
            dst_train_Label = train_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_train_Image)
            shutil.copyfile(srcLabel, dst_train_Label)
        elif i in val:
            dst_val_Image = val_image_path + name + '.jpg'
            dst_val_Label = val_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_val_Image)
            shutil.copyfile(srcLabel, dst_val_Label)
        else:
            dst_test_Image = test_image_path + name + '.jpg'
            dst_test_Label = test_label_path + name + '.txt'
            shutil.copyfile(srcImage, dst_test_Image)
            shutil.copyfile(srcLabel, dst_test_Label)


if __name__ == '__main__':
    main()

下面这个代码仅仅将每个数据的名字划分成训练集、验证集和测试集，上面那个会将图片和标注文件分别放到不同的文件夹。

这里是贴的B站一个博主的.py文件—Bubbliiiing！！这个博主人超好的

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

from utils.utils import get_classes

#--------------------------------------------------------------------------------------------------------------------------------#
#   annotation_mode用于指定该文件运行时计算的内容
#   annotation_mode为0代表整个标签处理过程，包括获得VOCdevkit/VOC2007/ImageSets里面的txt以及训练用的2007_train.txt、2007_val.txt
#   annotation_mode为1代表获得VOCdevkit/VOC2007/ImageSets里面的txt
#   annotation_mode为2代表获得训练用的2007_train.txt、2007_val.txt
#--------------------------------------------------------------------------------------------------------------------------------#
annotation_mode     = 0
#-------------------------------------------------------------------#
#   必须要修改，用于生成2007_train.txt、2007_val.txt的目标信息
#   与训练和预测所用的classes_path一致即可
#   如果生成的2007_train.txt里面没有目标信息
#   那么就是因为classes没有设定正确
#   仅在annotation_mode为0和2的时候有效
#-------------------------------------------------------------------#
classes_path = 'model_data/voc_classes.txt'  # 类别名称，例如person，cat，dog等等
#--------------------------------------------------------------------------------------------------------------------------------#
#   trainval_percent用于指定(训练集+验证集)与测试集的比例，默认情况下 (训练集+验证集):测试集 = 9:1 
#   train_percent用于指定(训练集+验证集)中训练集与验证集的比例，默认情况下 训练集:验证集 = 9:1 
#   仅在annotation_mode为0和1的时候有效
#--------------------------------------------------------------------------------------------------------------------------------#
trainval_percent = 0.9
train_percent = 0.9
#-------------------------------------------------------#
#   指向VOC数据集所在的文件夹
#   默认指向根目录下的VOC数据集
#-------------------------------------------------------#
VOCdevkit_path = 'VOCdevkit'

VOCdevkit_sets = [('2007', 'train'), ('2007', 'val')]
classes, _  = get_classes(classes_path)

def convert_annotation(year, image_id, list_file):
    in_file = open(os.path.join(VOCdevkit_path, 'VOC%s/Annotations/%s.xml'%(year, image_id)), encoding='utf-8')
    tree=ET.parse(in_file)
    root = tree.getroot()

    for obj in root.iter('object'):
        difficult = 0 
        if obj.find('difficult')!=None:
            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 = (int(float(xmlbox.find('xmin').text)), int(float(xmlbox.find('ymin').text)), int(float(xmlbox.find('xmax').text)), int(float(xmlbox.find('ymax').text)))
        list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))
        
if __name__ == "__main__":
    random.seed(0)
    if annotation_mode == 0 or annotation_mode == 1:
        print("Generate txt in ImageSets.")
        xmlfilepath = os.path.join(VOCdevkit_path, 'VOC2007/Annotations')
        saveBasePath = os.path.join(VOCdevkit_path, 'VOC2007/ImageSets/Main')
        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("train size",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()
        print("Generate txt in ImageSets done.")

    if annotation_mode == 0 or annotation_mode == 2:
        print("Generate 2007_train.txt and 2007_val.txt for train.")
        for year, image_set in VOCdevkit_sets:
            image_ids = open(os.path.join(VOCdevkit_path, 'VOC%s/ImageSets/Main/%s.txt'%(year, image_set)), encoding='utf-8').read().strip().split()
            list_file = open('%s_%s.txt'%(year, image_set), 'w', encoding='utf-8')
            for image_id in image_ids:
                list_file.write('%s/VOC%s/JPEGImages/%s.jpg'%(os.path.abspath(VOCdevkit_path), year, image_id))

                convert_annotation(year, image_id, list_file)
                list_file.write('\n')
            list_file.close()
        print("Generate 2007_train.txt and 2007_val.txt for train done.")