我一直在尝试使用Keras训练CNN，并将数据增强应用于一系列图像及其分割蒙版。在线示例说，为此，我应该使用flow_from_directory（）创建两个单独的生成器，然后将其压缩。
但是我可以只为图像和蒙版使用两个numpy数组，而是使用flow（）函数，而是这样做：
# Create image generator
data_gen_args = dict(rotation_range=5,
width_shift_range=0.1,
height_shift_range=0.1,
validation_split=0.2)
image_datagen = ImageDataGenerator(**data_gen_args)
seed = 1
# Create training and validation generators including masks
train_generator = image_datagen.flow(images, masks, seed=seed, subset='training')
val_train_generator = image_datagen.flow(images, masks, seed=seed, subset='validation')
# Train model
model.fit_generator(train_generator, steps_per_epoch=50,
validation_data = val_train_generator,
validation_steps = 10, shuffle=True, epochs=20)
如果没有，为什么不呢？看来，如果我运行生成器，那么我只能输出图像，而不能同时输出蒙版，因此我担心它没有按照我的意愿去做。
答案 0 :(得分：3)
您需要一个自定义生成器，该生成器将相同的增强应用于图像和蒙版。
Keras ImageDataGenerator接受2个参数（图像，标签或遮罩），并将转换应用于仅应用于第一个（图像）。您可以在下面使用我的生成器：
# Create image generator
data_gen_args = dict(rotation_range=5,
width_shift_range=0.1,
height_shift_range=0.1,
validation_split=0.2)
image_datagen = ImageDataGenerator(**data_gen_args)
seed = 1
def XYaugmentGenerator(X1, y, seed, batch_size):
genX1 = gen.flow(X1, y, batch_size=batch_size, seed=seed)
genX2 = gen.flow(y, X1, batch_size=batch_size, seed=seed)
while True:
X1i = genX1.next()
X2i = genX2.next()
yield X1i[0], X2i[0]
# Train model
model.fit_generator(XYaugmentGenerator(images, masks, seed, batch_size), steps_per_epoch=np.ceil(float(len(images)) / float(batch_size)),
validation_data = XYaugmentGenerator(images_valid, masks_valid, batch_size),
validation_steps = np.ceil(float(len(images_valid)) / float(batch_size))
, shuffle=True, epochs=20)
答案 1 :(得分：0)
根据我的实验，您不能仅使用zip(img_generator,mask_generator)。尽管不会发生错误，但它将永远运行。似乎它返回了一个无限生成器。要解决此问题，您可以使用while true:yield(img_generator.next(),mask_generator.next())。
答案 2 :(得分：0)
在深度学习中，对于细分问题，可以使用customer 'DataGenerator'函数而不是keras ImageDataGenerator。
DataGenerator？解决方案：
如果训练和测试图像位于文件夹中，而蒙版和标签位于csv中，请使用以下函数-自定义-DataGenerator：
class DataGenerator(keras.utils.Sequence):
'Generates data for Keras'
def __init__(self, list_IDs, df, target_df=None, mode='fit',
base_path='../train_images',
batch_size=16, dim=(1400, 2100), n_channels=3, reshape=None,
augment=False, n_classes=2, random_state=42, shuffle=True):
self.dim = dim
self.batch_size = batch_size
self.df = df
self.mode = mode
self.base_path = base_path
self.target_df = target_df
self.list_IDs = list_IDs
self.reshape = reshape
self.n_channels = n_channels
self.augment = augment
self.n_classes = n_classes
self.shuffle = shuffle
self.random_state = random_state
self.on_epoch_end()
np.random.seed(self.random_state)
def __len__(self):
'Denotes the number of batches per epoch'
return int(np.floor(len(self.list_IDs) / self.batch_size))
def __getitem__(self, index):
'Generate one batch of data'
# Generate indexes of the batch
indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]
# Find list of IDs
list_IDs_batch = [self.list_IDs[k] for k in indexes]
X = self.__generate_X(list_IDs_batch)
if self.mode == 'fit':
y = self.__generate_y(list_IDs_batch)
if self.augment:
X, y = self.__augment_batch(X, y)
return X, y
elif self.mode == 'predict':
return X
else:
raise AttributeError('The mode parameter should be set to "fit" or "predict".')
def on_epoch_end(self):
'Updates indexes after each epoch'
self.indexes = np.arange(len(self.list_IDs))
if self.shuffle == True:
np.random.seed(self.random_state)
np.random.shuffle(self.indexes)
def __generate_X(self, list_IDs_batch):
'Generates data containing batch_size samples'
# Initialization
if self.reshape is None:
X = np.empty((self.batch_size, *self.dim, self.n_channels))
else:
X = np.empty((self.batch_size, *self.reshape, self.n_channels))
# Generate data
for i, ID in enumerate(list_IDs_batch):
im_name = self.df['ImageId'].iloc[ID]
img_path = f"{self.base_path}/{im_name}"
img = self.__load_rgb(img_path)
if self.reshape is not None:
img = np_resize(img, self.reshape)
# Store samples
X[i,] = img
return X
def __generate_y(self, list_IDs_batch):
if self.reshape is None:
y = np.empty((self.batch_size, *self.dim, self.n_classes), dtype=int)
else:
y = np.empty((self.batch_size, *self.reshape, self.n_classes), dtype=int)
for i, ID in enumerate(list_IDs_batch):
im_name = self.df['ImageId'].iloc[ID]
image_df = self.target_df[self.target_df['ImageId'] == im_name]
rles = image_df['EncodedPixels'].values
if self.reshape is not None:
masks = build_masks(rles, input_shape=self.dim, reshape=self.reshape)
else:
masks = build_masks(rles, input_shape=self.dim)
y[i, ] = masks
return y
def __load_grayscale(self, img_path):
img = cv2.imread(img_path, cv2.IMREAD_GRAYSCALE)
img = img.astype(np.float32) / 255.
img = np.expand_dims(img, axis=-1)
return img
def __load_rgb(self, img_path):
img = cv2.imread(img_path)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = img.astype(np.float32) / 255.
return img
def __random_transform(self, img, masks):
composition = albu.Compose([
albu.HorizontalFlip(),
albu.VerticalFlip(),
albu.ShiftScaleRotate(rotate_limit=30, shift_limit=0.1)
#albu.ShiftScaleRotate(rotate_limit=90, shift_limit=0.2)
])
composed = composition(image=img, mask=masks)
aug_img = composed['image']
aug_masks = composed['mask']
return aug_img, aug_masks
def __augment_batch(self, img_batch, masks_batch):
for i in range(img_batch.shape[0]):
img_batch[i, ], masks_batch[i, ] = self.__random_transform(
img_batch[i, ], masks_batch[i, ])
return img_batch, masks_batch