将图像复制到训练、验证和测试的目录

shutil：高级的 文件、文件夹、压缩包 处理模块
shutil.copyfile(src, dst)：（copyfile只拷贝文件内容）拷贝文件
os.listdir()：方法用于返回指定的文件夹包含的文件或文件夹的名字的列表。这个列表以字母顺序。 它不包括 '.' 和'..' 即使它在文件夹中http://www.runoob.com/python/os-listdir.html

# 将图像复制到训练、验证和测试目录
import os, shutil

original_dataset_dir = 'D:/DeepLearning/kaggle/train' # 原始数据解压目录的路径

base_dir = 'D:/DeepLearning/kaggle/cats_and_dogs_small' # 保存较小的数据集的目录
os.mkdir(base_dir) # 创建一层目录

# 分别对应划分后的训练、验证和测试的目录
train_dir = os.path.join(base_dir, 'train') # 连接目录和文件名
os.mkdir(train_dir)
validation_dir = os.path.join(base_dir, 'validation')
os.mkdir(validation_dir)
test_dir = os.path.join(base_dir, 'test')
os.mkdir(test_dir)

# 猫的训练图像目录
train_cats_dir = os.path.join(train_dir, 'cats')
os.mkdir(train_cats_dir)

# 狗的训练图像目录
train_dogs_dir = os.path.join(train_dir, 'dogs')
os.mkdir(train_dogs_dir)

# 猫的验证图像目录
validation_cats_dir = os.path.join(validation_dir, 'cats')
os.mkdir(validation_cats_dir)

# 狗的验证图像目录
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
os.mkdir(validation_dogs_dir)

# 猫的测试图像目录
test_cats_dir = os.path.join(test_dir, 'cats')
os.mkdir(test_cats_dir)

# 狗的测试图像目录
test_dogs_dir = os.path.join(test_dir, 'dogs')
os.mkdir(test_dogs_dir)

# 将前1000张猫的图像复制到 train_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname) # 把目录和文件名合成一个路径
    dst = os.path.join(train_cats_dir, fname)
    shutil.copyfile(src, dst) # 拷贝文件

# 将接下来的500只猫的图像复制到 validation_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(1000, 1500)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(validation_cats_dir, fname)
    shutil.copyfile(src, dst)

# 将接下来的500只猫的图像复制到 test_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(1500, 2000)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(test_cats_dir, fname)
    shutil.copyfile(src, dst)

# 将1000张狗的图像复制到 train_dog_dir
fnames = ['dog.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(train_dogs_dir, fname)
    shutil.copyfile(src, dst)

# 将接下来500张狗的图像复制到 validation_dog_dir
fnames = ['dog.{}.jpg'.format(i) for i in range(1000, 1500)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(validation_dogs_dir, fname)
    shutil.copyfile(src, dst)

# 将接下来500张狗的图像复制到 test_dog_dir
fnames = ['dog.{}.jpg'.format(i) for i in range(1500, 2000)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(test_dogs_dir, fname)
    shutil.copyfile(src, dst)

print('total training cat images: ', len(os.listdir(train_cats_dir)))
print('total training dog images: ', len(os.listdir(train_dogs_dir)))
print('total validation cat images: ', len(os.listdir(validation_cats_dir)))
print('total validation dog images: ', len(os.listdir(validation_dogs_dir)))
print('total test cat images: ', len(os.listdir(test_cats_dir)))
print('total test dog images: ', len(os.listdir(test_dogs_dir)))

total training cat images:  1000
total training dog images:  1000
total validation cat images:  500
total validation dog images:  500
total test cat images:  500
total test dog images:  500

2000张训练图像、1000张验证图像、1000张测试图像

哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈