Data preparation for Dogs vs. Cats

data_preparation

# Create smaller dataset for Dogs vs. Cats
import os, shutil

original_dataset_dir = '/Users/macbook/dogs_cats_dataset/train/'

base_dir = '/Users/macbook/book/dogs_cats/data'
if not os.path.exists(base_dir):
    os.mkdir(base_dir)

# Create directories
train_dir = os.path.join(base_dir,'train')
if not os.path.exists(train_dir):
    os.mkdir(train_dir)
validation_dir = os.path.join(base_dir,'validation')
if not os.path.exists(validation_dir):
    os.mkdir(validation_dir)
test_dir = os.path.join(base_dir,'test')
if not os.path.exists(test_dir):
    os.mkdir(test_dir)

train_cats_dir = os.path.join(train_dir,'cats')
if not os.path.exists(train_cats_dir):
    os.mkdir(train_cats_dir)

train_dogs_dir = os.path.join(train_dir,'dogs')
if not os.path.exists(train_dogs_dir):
    os.mkdir(train_dogs_dir)

validation_cats_dir = os.path.join(validation_dir,'cats')
if not os.path.exists(validation_cats_dir):
    os.mkdir(validation_cats_dir)

validation_dogs_dir = os.path.join(validation_dir, 'dogs')
if not os.path.exists(validation_dogs_dir):
    os.mkdir(validation_dogs_dir)

test_cats_dir = os.path.join(test_dir, 'cats')     
if not os.path.exists(test_cats_dir):
    os.mkdir(test_cats_dir)

test_dogs_dir = os.path.join(test_dir, 'dogs')
if not os.path.exists(test_dogs_dir):
    os.mkdir(test_dogs_dir)

# Copy first 1000 cat images to train_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(100)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(train_cats_dir, fname)
    shutil.copyfile(src, dst)
    
# Copy next 500 cat images to validation_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(200, 250)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(validation_cats_dir, fname)
    shutil.copyfile(src, dst)
    
# Copy next 500 cat images to test_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(250,300)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(test_cats_dir, fname)
    shutil.copyfile(src, dst)
    
# Copy first 1000 dog images to train_dogs_dir
fnames = ['dog.{}.jpg'.format(i) for i in range(100)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(train_dogs_dir, fname)
    shutil.copyfile(src, dst)
                                                
# Copy next 500 dog images to validation_dogs_dir
fnames = ['dog.{}.jpg'.format(i) for i in range(200,250)]
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(250,300)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(test_dogs_dir, fname)
    shutil.copyfile(src, dst)
                                                
# Sanity checks
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)))