# 将数据集随机划分为训练集和验证集,测试集-Toy模板网

这篇具有很好参考价值的文章主要介绍了# 将数据集随机划分为训练集和验证集,测试集。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

# 将数据集随机划分为训练集和验证集,测试集
import os
import random
import shutil

from tqdm import tqdm

image_path = r'F:\Dissertation\3.Sub-Topic-C\Datasets\0.Ship Detection from Aerial Images_datasets\images\\'  # 源图片文件夹路径
mask_path = r'F:\Dissertation\3.Sub-Topic-C\Datasets\0.Ship Detection from Aerial Images_datasets\annotations\\'  # 标签文件夹路径

train_images = r'F:\Dissertation\3.Sub-Topic-C\Datasets\0.Ship Detection from Aerial Images_datasets\VOC\train\images'  # 划分后训练集图片的保存路径
train_labels = r'F:\Dissertation\3.Sub-Topic-C\Datasets\0.Ship Detection from Aerial Images_datasets\VOC\train\labels'
val_images = r'F:\Dissertation\3.Sub-Topic-C\Datasets\0.Ship Detection from Aerial Images_datasets\VOC\val\images'
val_labels = r'F:\Dissertation\3.Sub-Topic-C\Datasets\0.Ship Detection from Aerial Images_datasets\VOC\val\labels'
# test_images = r'E:\DCI(first)_3\DCI_Split2\test\images'
# test_labels = r'E:\DCI(first)_3\DCI_Split2\test\labels'

if not os.path.exists(train_images):
    os.makedirs(train_images)
if not os.path.exists(train_labels):
    os.makedirs(train_labels)
if not os.path.exists(val_images):
    os.makedirs(val_images)
if not os.path.exists(val_labels):
    os.makedirs(val_labels)
# if not os.path.exists(test_images):
#     os.makedirs(test_images)
# if not os.path.exists(test_labels):
#     os.makedirs(test_labels)
train_rate = 0.8  # 自定义抽取图片的比例，比方说100张抽10张，那就是0.1
val_rate = 0.2
#test_rate = 0.15
# 求训练集
pathDir = os.listdir(image_path)  # 取图片的原始路径
print('数据集总共有图片:', len(pathDir))
print(
    '划分比例如下：训练集:{},验证集:{}'.format(int(len(pathDir) * train_rate), int(len(pathDir) * val_rate),
                                         )) #,测试集:{}   int(len(pathDir) * test_rate)
picknumber = int(len(pathDir) * train_rate)  # 按照rate比例从文件夹中取一定数量图片
train_sample = random.sample(pathDir, picknumber)  # 随机选取picknumber数量的样本图片
print('训练集的大小为：', len(train_sample))

# 复制为训练集
for name in tqdm(train_sample):
    shutil.copy(image_path + name, train_images + "\\" + name)
    shutil.copy(mask_path + name[:-3] + "xml", train_labels + "\\" + name[:-3] + "xml")

# 求出原数据集不含训练集
all_images = os.listdir(image_path)
remaining_image = []
for file in all_images:
    if file not in train_sample:
        remaining_image.append(file)
# 求验证集
picknumber2 = int(len(remaining_image) * val_rate / (val_rate ))  # 按照rate比例从文件夹中取一定数量图片 + test_rate
val_sample = random.sample(remaining_image, picknumber2)  # 随机选取picknumber数量的样本图片
print('验证集的大小为：', len(val_sample))
# 复制为验证集
for file in tqdm(val_sample):
    shutil.copy(image_path + file, val_images + "\\" + file)
    shutil.copy(mask_path + file[:-3] + "xml", val_labels + "\\" + file[:-3] + "xml")

# test_sample = []
# for file in remaining_image:
#     if file not in val_sample:
#         test_sample.append(file)
# print('测试集的大小为：', len(test_sample))
# # 复制为测试集
# for file in tqdm(test_sample):
#     shutil.copy(image_path + file, test_images + "\\" + file)
#     shutil.copy(mask_path + file, test_labels + "\\" + file)

文章来源地址https://www.toymoban.com/news/detail-495004.html

到了这里，关于# 将数据集随机划分为训练集和验证集,测试集的文章就介绍完了。如果您还想了解更多内容，请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章，希望大家以后多多支持TOY模板网！