方式一 : 加载图片到内存
1.优点 :
不用对数据进行分类
2.缺点 :
对内存要求高,如果数据量过大,内存容量不够,容易造成电脑系统崩溃
3.适用文件存储方式 :
图片没有根据标签分文件夹
4.代码实现
- 定义文件夹路径
TRAIN_DATA_PATH = 'E:/mldata/dogvscat/data/train/'
TEST_DATA_PATH = 'E:/mldata/dogvscat/data//test1/'
- 读取图片制作数据集
imgs_per_cat = 1000
image_size = (200, 200)
labels = []
train_images = []
for item in os.listdir(TRAIN_DATA_PATH):
print("train----" + str(item))
img = image.load_img(os.path.join(TRAIN_DATA_PATH, str(item)), target_size=image_size)
img = image.img_to_array(img)
img = img / 255.
train_images.append(img)
labels.append(item.split('.')[0])
X = np.array(train_images)
y = []
for item in labels:
print("labels------" + str(item))
if item == 'cat':
y.append(0)
else:
y.append(1)
new_labels = pd.get_dummies(labels)
- 使用sklearn 中的train_test_split划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, new_labels, random_state=42, test_size=0.2)- 训练方式:
model.fit(X_train, y_train, batch_size=32, epochs=100, validation_split=0.3)方式二 : 使用keras 的 ImageDataGenerator分批加载数据
1.优点 :
分批加载数据
2.缺点 :
需要对数据进行按标签分文件夹
3.适用文件存储方式 :
图片根据标签对数据分文件夹
4.实现方式：
- 创建文件夹
base_dir = 'E:/mldata/dogvscat/cats_and_dogs_small'
os.mkdir(base_dir)
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)
train_cats_dir = os.path.join(train_dir, 'cats')
os.mkdir(train_cats_dir)
train_dogs_dir = os.path.join(train_dir, 'dogs')
os.mkdir(train_dogs_dir)
validation_cats_dir = os.path.join(validation_dir, 'cats')
os.mkdir(validation_cats_dir)
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
os.mkdir(validation_dogs_dir)
test_cats_dir = os.path.join(test_dir, 'cats')
os.mkdir(test_cats_dir)
test_dogs_dir = os.path.join(test_dir, 'dogs')
os.mkdir(test_dogs_dir)- 复制文件到文件夹
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.copyfile(src, dst)
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)
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)
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)
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)
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)
- 使用 ImageDataGenerator 加载数据
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
train_dir,
target_size=(150, 150),
batch_size=20,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
validation_dir,
target_size=(150, 150),
batch_size=20,
class_mode='binary')- 训练方式
history = model.fit_generator(
train_generator,
steps_per_epoch=100,
epochs=30,
validation_data=validation_generator,
validation_steps=50)