python - 为多类道路分割实现 U-net

Question

我正在尝试训练一个 U-net 以对卫星数据进行图像分割，并由此提取具有九种不同道路类型的道路网络。到目前为止，我已经尝试了很多不同的 U-net 代码，这些代码可以在网络上免费获得，但是我无法根据我的具体情况对它们进行定制。我真诚地希望你能帮助我。

可以通过以下链接下载卫星图像和相关标签: Satellite image and associated labels

此外，我编写了以下代码来为 Unet 准备数据

import skimage
from skimage.io import imread, imshow, imread_collection, concatenate_images
from skimage.transform import resize
from skimage.morphology import label
import numpy as np
import matplotlib.pyplot as plt
from keras.models import Model
from keras.layers import Input, merge, Convolution2D, MaxPooling2D, UpSampling2D, Reshape, core, Dropout
from keras.optimizers import Adam
from keras.callbacks import ModelCheckpoint, LearningRateScheduler
from keras import backend as K
from sklearn.metrics import jaccard_similarity_score
from shapely.geometry import MultiPolygon, Polygon
import shapely.wkt
import shapely.affinity
from collections import defaultdict

#Importing image and labels
labels = skimage.io.imread("ede_subset_293_wegen.tif")
images = skimage.io.imread("ede_subset_293_20180502_planetscope.tif")[...,:-1]

#Scaling image
img_scaled = images / images.max()

#Make non-roads 0
labels[labels == 15] = 0

#Resizing image and mask and labels
img_scaled_resized = img_scaled[:6400, :6400,:4 ]
print(img_scaled_resized.shape)
labels_resized = labels[:6400, :6400]
print(labels_resized.shape)

#splitting images
split_img = [
    np.split(array, 25, axis=0) 
    for array in np.split(img_scaled_resized, 25, axis=1)
]

split_img[-1][-1].shape

#splitting labels
split_labels = [
    np.split(array, 25, axis=0) 
    for array in np.split(labels_resized, 25, axis=1)
]

#Convert to np.array
split_labels = np.array(split_labels)
split_img = np.array(split_img)

train_images = np.reshape(split_img, (625, 256, 256, 4))
train_labels = np.reshape(split_labels, (625, 256, 256))

x_trn = train_images[:400,:,:,:]
x_val = train_images[400:500,:,:,:]
x_test = train_images[500:625,:,:,:]

y_trn = train_labels[:400,:,:]
y_val = train_labels[400:500,:,:]
y_test = train_labels[500:625,:,:]

plt.imshow(train_images[88,:,:,:])
skimage.io.imshow(train_labels[88,:,:])

此外，我在 kaggle 上发现了以下 U-net，我认为它应该适用于这种特殊情况:

def get_unet():
    inputs = Input((8, ISZ, ISZ))
    conv1 = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(inputs)
    conv1 = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)

    conv2 = Convolution2D(64, 3, 3, activation='relu', border_mode='same')(pool1)
    conv2 = Convolution2D(64, 3, 3, activation='relu', border_mode='same')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)

    conv3 = Convolution2D(128, 3, 3, activation='relu', border_mode='same')(pool2)
    conv3 = Convolution2D(128, 3, 3, activation='relu', border_mode='same')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)

    conv4 = Convolution2D(256, 3, 3, activation='relu', border_mode='same')(pool3)
    conv4 = Convolution2D(256, 3, 3, activation='relu', border_mode='same')(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)

    conv5 = Convolution2D(512, 3, 3, activation='relu', border_mode='same')(pool4)
    conv5 = Convolution2D(512, 3, 3, activation='relu', border_mode='same')(conv5)

    up6 = merge([UpSampling2D(size=(2, 2))(conv5), conv4], mode='concat', concat_axis=1)
    conv6 = Convolution2D(256, 3, 3, activation='relu', border_mode='same')(up6)
    conv6 = Convolution2D(256, 3, 3, activation='relu', border_mode='same')(conv6)

    up7 = merge([UpSampling2D(size=(2, 2))(conv6), conv3], mode='concat', concat_axis=1)
    conv7 = Convolution2D(128, 3, 3, activation='relu', border_mode='same')(up7)
    conv7 = Convolution2D(128, 3, 3, activation='relu', border_mode='same')(conv7)

    up8 = merge([UpSampling2D(size=(2, 2))(conv7), conv2], mode='concat', concat_axis=1)
    conv8 = Convolution2D(64, 3, 3, activation='relu', border_mode='same')(up8)
    conv8 = Convolution2D(64, 3, 3, activation='relu', border_mode='same')(conv8)

    up9 = merge([UpSampling2D(size=(2, 2))(conv8), conv1], mode='concat', concat_axis=1)
    conv9 = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(up9)
    conv9 = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(conv9)

    conv10 = Convolution2D(N_Cls, 1, 1, activation='sigmoid')(conv9)

    model = Model(input=inputs, output=conv10)
    model.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=[jaccard_coef, jaccard_coef_int, 'accuracy'])
    return model

我知道这是一个大问题，但我非常绝望。非常感谢任何帮助!

Answer 1

我发现 Conv2DTranspose 比 UpSampling2D 效果更好，这里是使用相同方法的快速实现

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

现在对于数据生成器，您可以使用内置的 ImageDataGenerator 类这是来自 Keras 文档的代码

# 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)

另一种方法是通过扩展 Keras 的 Sequence 类来实现您自己的生成器

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)

这是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)

当我只有两个类时，我尝试使用骰子损失，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