copy_images.py

import os, shutil

# 原数据集的目录
original_dataset_dir = 'E:/BaiduNetdiskDownload/train'

# 小数据集的目录
base_dir = 'cats_and_dogs_small'
os.mkdir(base_dir)

# 为训练集、验证集和测试集划分目录
train_dir = os.path.join(base_dir, 'train')
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)

# 训练集中的猫图片的目录
train_cats_dir = os.path.join(train_dir, 'cats')
os.mkdir(train_cats_dir)

# 训练集中的狗图片的目录
train_dogs_dir = os.path.join(train_dir, 'dogs')
os.mkdir(train_dogs_dir)

# 验证集中的猫图片的目录
validation_cats_dir = os.path.join(validation_dir, 'cats')
os.mkdir(validation_cats_dir)

# 验证集中的狗图片的目录
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
os.mkdir(validation_dogs_dir)

# 测试集中的猫图片的目录
test_cats_dir = os.path.join(test_dir, 'cats')
os.mkdir(test_cats_dir)

# 测试集中的狗图片的目录
test_dogs_dir = os.path.join(test_dir, 'dogs')
os.mkdir(test_dogs_dir)

# 复制前1000张猫图片到训练集猫图片目录中
fnames = ['cat.{}.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_cats_dir, fname)
    shutil.copy(src, dst)

# 复制下500张猫图片到验证集猫图片目录中
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.copy(src, dst)

# 复制下500张猫图片到测试集猫图片目录中
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.copy(src, dst)

# 复制前1000张狗图片到训练集狗图片目录中
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.copy(src, dst)

# 复制下500张狗图片到验证集狗图片目录中
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.copy(src, dst)

# 复制下500张狗图片到测试集狗图片目录中
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.copy(src, dst)

# 验证每个文件夹下的图片数
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)))