keras貓狗大戰

先划分數據集程序訓練集中貓狗各12500張現在提取1000張做為訓練集，500張作為測試集，500張作為驗證集：

# -*- coding: utf-8 -*-
import os, shutil

original_dataset_dir = '/home/duchao/projects(my)/keras/kagge/train' # 原始文解壓目錄
base_dir = '/home/duchao/projects(my)/keras/kagge/small_data'
# 創建新的文件夾
os.mkdir(base_dir)

# 分別對應划分好的訓練(1000)，驗證(500)和測試目錄(500)
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)

# 貓的訓練目錄
train_cats_dir = os.path.join(train_dir, 'cats')
os.mkdir(train_cats_dir)

# 狗的訓練目錄
train_dogs_dir = os.path.join(train_dir, 'dogs')
os.mkdir(train_dogs_dir)

# 貓的驗證目錄
validation_cats_dir = os.path.join(validation_dir, 'cats')
os.mkdir(validation_cats_dir)

# 狗的驗證目錄
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
os.mkdir(validation_dogs_dir)

# 貓的測試目錄
test_cats_dir = os.path.join(test_dir, 'cats')
os.mkdir(test_cats_dir)

# 狗的測試目錄
test_dogs_dir = os.path.join(test_dir, 'dogs')
os.mkdir(test_dogs_dir)

# 將前1000張貓的圖像復制到train_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(1000)] # format函數通過{}來指點字符串處理的位置，儲存為列表形式
for fname in fnames:
 src = os.path.join(original_dataset_dir, fname)
 dst = os.path.join(train_cats_dir, fname)
 shutil.copyfile(src, dst) # copyfile實現將一個文件中的內容復制道另一個文件中去，src是來源文件；dst是目標文件

# 將剩下的500張圖像復制到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)

# 將接下來500張圖片復制到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)

# 將前1000張狗的圖片復制到train_dogs_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)

# 將接下來500張圖像復制到validation_dogs_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)

# Copy next 500 dog images to test_dogs_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))) #os.listdir列舉指定目錄中的文件名
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)))