1. 按比例划分分类所需数据集
import os import random import shutil import time def copyFile(fileDir, class_name): image_list = os.listdir(fileDir) # 获取图片的原始路径 image_number = len(image_list) train_number = int(image_number * train_rate) train_sample = random.sample(image_list, train_number) # 从image_list中随机获取0.8比例的图像. test_sample = list(set(image_list) - set(train_sample)) sample = [train_sample, test_sample] # 复制图像到目标文件夹 for k in range(len(save_dir)): if os.path.isdir(save_dir[k] + class_name): for name in sample[k]: shutil.copy(os.path.join(fileDir, name), os.path.join(save_dir[k] + class_name+'/', name)) else: os.makedirs(save_dir[k] + class_name) for name in sample[k]: shutil.copy(os.path.join(fileDir, name), os.path.join(save_dir[k] + class_name+'/', name)) if __name__ == '__main__': time_start = time.time() # 原始数据集路径 origion_path = 'F:/1/' # 保存路径 save_train_dir = 'F:/1/train/' save_test_dir = 'F:/1/test/' save_dir = [save_train_dir, save_test_dir] # 训练集比例 train_rate = 0.8 # 数据集类别及数量 file_list = os.listdir(origion_path) num_classes = len(file_list) for i in range(num_classes): class_name = file_list[i] image_Dir = os.path.join(origion_path, class_name) copyFile(image_Dir, class_name) print('%s划分完毕!' % class_name) time_end = time.time() print('---------------') print('训练集和测试集划分共耗时%s!' % (time_end - time_start))
讯享网
2. 划分VOC数据集
讯享网import os import random trainval_percent = 0.8 train_percent = 0.75 xmlfilepath = 'C:/Users/123/Desktop/VOC2007/Annotations' txtsavepath = 'C:/Users/123/Desktop/VOC2007/ImageSets/Main' total_xml = os.listdir(xmlfilepath) 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) ftrainval = open('C:/Users/123/Desktop/VOC2007/ImageSets/Main/trainval.txt', 'w') ftest = open('C:/Users/123/Desktop/VOC2007/ImageSets/Main/test.txt', 'w') ftrain = open('C:/Users/123/Desktop/VOC2007/ImageSets/Main/train.txt', 'w') fval = open('C:/Users/123/Desktop/VOC2007/ImageSets/Main/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()

版权声明:本文内容由互联网用户自发贡献,该文观点仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容,请联系我们,一经查实,本站将立刻删除。
如需转载请保留出处:https://51itzy.com/kjqy/115707.html