分割数据集为训练集和测试集

最新推荐文章于 2024-03-30 16:29:35 发布

IEnigma

最新推荐文章于 2024-03-30 16:29:35 发布

阅读量868

点赞数

文章标签：深度学习 tensorflow

本文链接：https://blog.csdn.net/IEnigma/article/details/115756880

版权

//分割函数
import os 
import shutil

def split_data(SOURCE,TRAINING,TESTING,SPLIT_SIZE):
    files = []
    for filename in os.listdir(SOURCE):
        file = SOURCE + filename
        if os.path.getsize(file) > 0:
            files.append(filename)
        else:
            print(filename + " is zero length,so ignoring.")
    
    training_length = int(len(files) * SPLIT_SIZE)
    testing_length = int(len(files) - training_length)
    shuffled_set = random.sample(files,len(files))
    training_set = shuffled_set[0:training_length]
    testing_set = shuffled_set[-testing_length:]
    
    for filename in training_set:
        this_file = SOURCE + filename
        destination = TRAINING + filename
        copyfile(this_file,destination)
        
    for filename in testing_set:
        this_file = SOURCE + filename
        destination = TESTING + filename
        copyfile(this_file,destination)

// 创建训练集和测试集的文件夹
def create_dir(file_dir):
    if os.path.exists(file_dir):
        print('ture')
        shutil.rmtree(file_dir)#删除再建立
        os.makedirs(file_dir)
    else:
        os.makedirs(file_dir)

CAT_SOURCE_DIR = "/tmp/PetImages/Cat/"
TRAINING_CATS_DIR = "/tmp/cats-v-dogs/training/cats/"
TESTING_CATS_DIR = "/tmp/cats-v-dogs/testing/cats/"
DOG_SOURCE_DIR = "/tmp/PetImages/Dog/"
TRAINING_DOGS_DIR = "/tmp/cats-v-dogs/training/dogs/"
TESTING_DOGS_DIR = "/tmp/cats-v-dogs/testing/dogs/"

create_dir(TRAINING_CATS_DIR)
create_dir(TESTING_CATS_DIR)
create_dir(TRAINING_DOGS_DIR)
create_dir(TESTING_CATS_DIR)
#带入函数，进行分割
split_size = .9
split_data(CAT_SOURCE_DIR,TRAINING_CATS_DIR,TESTING_CATS_DIR,split_size)
split_data(DOG_SOURCE_DIR,TRAINING_DOGS_DIR,TESTING_DOGS_DIR,split_size)