Keras：使用灰度蒙版和ImageDataGenerator类进行图像分割

Question

我目前正在尝试使用Keras 2.1.6（以TensorFlow作为后端）及其ImageDataGenerator来实现卷积网络，以使用灰度蒙版分割图像。我尝试使用图像作为输入，并使用遮罩作为标签。由于训练图像数量少，并且内存有限，因此我使用了Keras中提供的ImageDataGenerator类。

但是，在将Keras示例中提供的值更改为稍后描述的值之后，我得到了此错误：

File "C:\Users\XXX\Anaconda3\lib\site-packages\keras\engine\training.py", line 2223, in fit_generator
batch_size = x.shape[0]
AttributeError: 'tuple' object has no attribute 'shape'

据我所知，发生这种情况的原因是生成器确实生成了元组而不是数组。这是在我将以下参数从Keras示例中提供的标准值更改为以下参数后第一次发生的：对于所有掩码生成器，color_mode='grayscale'；对于自动编码器，建议使用class_mode='input'。

可在here中找到Keras示例。

我正在使用的数据集由100张图像（jpg）和100个相应的灰度蒙版（png）组成，可以从this link下载

我要实现的体系结构是基于自动编码器/ U-Net的网络，并在提供的代码中显示：

from keras.preprocessing import image
from keras.models import Model
from keras import optimizers 
from keras.preprocessing.image import ImageDataGenerator
from keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D
from keras import initializers

image_path = 
mask_path = 
valid_image_path = 
valid_mask_path = 

img_size=160
batchsize=10
samplesize = 60
steps = samplesize / batchsize

train_datagen = image.ImageDataGenerator(shear_range=0.2,
                                        zoom_range=0.2,
                                        horizontal_flip=True)

data_gen_args = dict(rotation_range=90,
                     width_shift_range=0.1,
                     height_shift_range=0.1,
                     zoom_range=0.2)

image_datagen = ImageDataGenerator(**data_gen_args)
mask_datagen = ImageDataGenerator(**data_gen_args)

seed = 1

image_generator = image_datagen.flow_from_directory(
    image_path,
    target_size=(img_size, img_size),
    class_mode='input',
    batch_size = batchsize,
    seed=seed)

mask_generator = mask_datagen.flow_from_directory(
    mask_path,
    target_size=(img_size, img_size),
    class_mode='input',
    color_mode = 'grayscale',
    batch_size = batchsize,
    seed=seed)

vimage_generator = image_datagen.flow_from_directory(
    valid_image_path,
    target_size=(img_size, img_size),
    class_mode='input',
    batch_size = batchsize,
    seed=seed)

vmask_generator = mask_datagen.flow_from_directory(
    valid_mask_path,
    target_size=(img_size, img_size),
    class_mode='input',
    color_mode = 'grayscale',
    batch_size = batchsize,
    seed=seed)

#Model 
input_img = Input(shape=(img_size,img_size,3))
c11 = Conv2D(16, (3, 3), activation='relu', padding='same', kernel_initializer=initializers.random_normal(stddev=0.01))(input_img)
mp1 = MaxPooling2D((2, 2), padding='same')(c11)
c21 = Conv2D(16, (3, 3), activation='relu', padding='same', kernel_initializer=initializers.random_normal(stddev=0.01))(mp1)
mp2 = MaxPooling2D((2, 2), padding='same')(c21)
c31 = Conv2D(32, (3, 3), activation='relu', padding='same', kernel_initializer=initializers.random_normal(stddev=0.01))(mp2)
encoded = MaxPooling2D((5, 5), padding='same')(c31)

c12 = Conv2D(32, (3, 3), activation='relu', padding='same', kernel_initializer=initializers.random_normal(stddev=0.01))(encoded)
us12 = UpSampling2D((5,5))(c12)
c22 = Conv2D(16, (3, 3), activation='relu', padding='same', kernel_initializer=initializers.random_normal(stddev=0.01))(us12)
us22 = UpSampling2D((2, 2))(c22)
c32 = Conv2D(16, (3, 3), activation='relu', padding='same', kernel_initializer=initializers.random_normal(stddev=0.01))(us22)
us32 = UpSampling2D((2, 2))(c32)
decoded = Conv2D(1, (3, 3), activation='softmax', padding='same')(us32)

model = Model(input_img, decoded)

model.compile(loss="mean_squared_error", optimizer=optimizers.Adam(),metrics=["accuracy"])
#model.summary()

#Generators, tr: training, v: validation
trgen = zip(image_generator,mask_generator)
vgen = zip(vimage_generator,vmask_generator)

model.fit_generator(
    trgen,
    steps_per_epoch= steps,
    epochs=5,
    validation_data = vgen,
    validation_steps=10)

Answer 1

您要构建的是图像分割模型，而不是自动编码器。因此，由于您有图像和标签（即蒙版）的单独生成器，因此需要将class_mode参数设置为None，以防止生成器生成任何标签数组。

此外，您需要将最后一层的激活功能从softmax更改为sigmoid，否则，由于softmax将其输入元素的总和标准化为1，因此输出将全部为1。您也可以将binary_crossentropy用于损失函数。

Answer 2

这是Unet的更好版本，您可以使用此代码

def conv_block(tensor, nfilters, size=3, padding='same', initializer="he_normal"):
    x = Conv2D(filters=nfilters, kernel_size=(size, size), padding=padding, kernel_initializer=initializer)(tensor)
    x = BatchNormalization()(x)
    x = Activation("relu")(x)
    x = Conv2D(filters=nfilters, kernel_size=(size, size), padding=padding, kernel_initializer=initializer)(x)
    x = BatchNormalization()(x)
    x = Activation("relu")(x)
    return x


def deconv_block(tensor, residual, nfilters, size=3, padding='same', strides=(2, 2)):
    y = Conv2DTranspose(nfilters, kernel_size=(size, size), strides=strides, padding=padding)(tensor)
    y = concatenate([y, residual], axis=3)
    y = conv_block(y, nfilters)
    return y


def Unet(img_height, img_width, nclasses=3, filters=64):
# down
    input_layer = Input(shape=(img_height, img_width, 3), name='image_input')
    conv1 = conv_block(input_layer, nfilters=filters)
    conv1_out = MaxPooling2D(pool_size=(2, 2))(conv1)
    conv2 = conv_block(conv1_out, nfilters=filters*2)
    conv2_out = MaxPooling2D(pool_size=(2, 2))(conv2)
    conv3 = conv_block(conv2_out, nfilters=filters*4)
    conv3_out = MaxPooling2D(pool_size=(2, 2))(conv3)
    conv4 = conv_block(conv3_out, nfilters=filters*8)
    conv4_out = MaxPooling2D(pool_size=(2, 2))(conv4)
    conv4_out = Dropout(0.5)(conv4_out)
    conv5 = conv_block(conv4_out, nfilters=filters*16)
    conv5 = Dropout(0.5)(conv5)
# up
    deconv6 = deconv_block(conv5, residual=conv4, nfilters=filters*8)
    deconv6 = Dropout(0.5)(deconv6)
    deconv7 = deconv_block(deconv6, residual=conv3, nfilters=filters*4)
    deconv7 = Dropout(0.5)(deconv7) 
    deconv8 = deconv_block(deconv7, residual=conv2, nfilters=filters*2)
    deconv9 = deconv_block(deconv8, residual=conv1, nfilters=filters)
# output
    output_layer = Conv2D(filters=nclasses, kernel_size=(1, 1))(deconv9)
    output_layer = BatchNormalization()(output_layer)
    output_layer = Activation('softmax')(output_layer)

    model = Model(inputs=input_layer, outputs=output_layer, name='Unet')
    return model

请注意，如果只有两个类，即nclasses = 2，则需要更改

output_layer = Conv2D(filters=nclasses, kernel_size=(1, 1))(deconv9)
output_layer = BatchNormalization()(output_layer)
output_layer = Activation('softmax')(output_layer)

到

output_layer = Conv2D(filters=2, kernel_size=(1, 1))(deconv9)
output_layer = BatchNormalization()(output_layer)
output_layer = Activation('sigmoid')(output_layer)

现在对于数据生成器，您可以使用内置的ImageDataGenerator类 这是Keras文档中的代码

# we create two instances with the same arguments
data_gen_args = dict(featurewise_center=True,
                     featurewise_std_normalization=True,
                     rotation_range=90,
                     width_shift_range=0.1,
                     height_shift_range=0.1,
                     zoom_range=0.2)
image_datagen = ImageDataGenerator(**data_gen_args)
mask_datagen = ImageDataGenerator(**data_gen_args)

# Provide the same seed and keyword arguments to the fit and flow methods
seed = 1
image_datagen.fit(images, augment=True, seed=seed)
mask_datagen.fit(masks, augment=True, seed=seed)

image_generator = image_datagen.flow_from_directory(
    'data/images',
    class_mode=None,
    seed=seed)

mask_generator = mask_datagen.flow_from_directory(
    'data/masks',
    class_mode=None,
    seed=seed)

# combine generators into one which yields image and masks
train_generator = zip(image_generator, mask_generator)

model.fit_generator(
    train_generator,
    steps_per_epoch=2000,
    epochs=50)

另一种可行的方法是通过从Keras扩展Sequence类来实现自己的生成器

class seg_gen(Sequence):
    def __init__(self, x_set, y_set, batch_size, image_dir, mask_dir):
        self.x, self.y = x_set, y_set
        self.batch_size = batch_size
        self.samples = len(self.x)
        self.image_dir = image_dir
        self.mask_dir = mask_dir

    def __len__(self):
        return int(np.ceil(len(self.x) / float(self.batch_size)))

    def __getitem__(self, idx):
        idx = np.random.randint(0, self.samples, batch_size)
        batch_x, batch_y = [], []
        drawn = 0
        for i in idx:
            _image = image.img_to_array(image.load_img(f'{self.image_dir}/{self.x[i]}', target_size=(img_height, img_width)))/255.   
            mask = image.img_to_array(image.load_img(f'{self.mask_dir}/{self.y[i]}', grayscale=True, target_size=(img_height, img_width)))
#             mask = np.resize(mask,(img_height*img_width, classes))
            batch_y.append(mask)
            batch_x.append(_image)
        return np.array(batch_x), np.array(batch_y)

以下是用于训练模型的示例代码

unet = Unet(256, 256, nclasses=66, filters=64)
print(unet.output_shape)
p_unet = multi_gpu_model(unet, 4)
p_unet.load_weights('models-dr/top_weights.h5')
p_unet.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
tb = TensorBoard(log_dir='logs', write_graph=True)
mc = ModelCheckpoint(mode='max', filepath='models-dr/top_weights.h5', monitor='acc', save_best_only='True', save_weights_only='True', verbose=1)
es = EarlyStopping(mode='max', monitor='acc', patience=6, verbose=1)
callbacks = [tb, mc, es]
train_gen = seg_gen(image_list, mask_list, batch_size)


p_unet.fit_generator(train_gen, steps_per_epoch=steps, epochs=13, callbacks=callbacks, workers=8)

当我只有2个班级使用骰子损失时，我获得了不错的成绩，这是它的代码

def dice_coeff(y_true, y_pred):
    smooth = 1.
    y_true_f = K.flatten(y_true)
    y_pred_f = K.flatten(y_pred)
    intersection = K.sum(y_true_f * y_pred_f)
    score = (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)
    return score

def dice_loss(y_true, y_pred):
    loss = 1 - dice_coeff(y_true, y_pred)
    return loss