各主流分割网络的keras实现

1.keras实现unet

def unet(input_size = (512,512,3),base_filter_num=64):
    inputs = Input(input_size)
    conv1 = Conv2D(base_filter_num, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(inputs)
    conv1 = Conv2D(base_filter_num, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)

    conv2 = Conv2D(base_filter_num*2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
    conv2 = Conv2D(base_filter_num*2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)

    conv3 = Conv2D(base_filter_num*4, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
    conv3 = Conv2D(base_filter_num*4, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)

    conv4 = Conv2D(base_filter_num*8, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
    conv4 = Conv2D(base_filter_num*8, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)

    conv5 = Conv2D(base_filter_num*16, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
    conv5 = Conv2D(base_filter_num*16, 3, activation = 'relu', padding = 'same', kernelinitializer = 'he_normal')(conv5)

    up6 = Conv2DTranspose(base_filter_num*8, (2, 2), strides=(2, 2), padding='same')(conv5)
    # up6 = Conv2D(base_filter_num*8, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv5))
    merge6 = concatenate([conv4,up6], axis = -1)
    conv6 = Conv2D(base_filter_num*8, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
    conv6 = Conv2D(base_filter_num*8, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)

    up7 = Conv2DTranspose(base_filter_num*4, (2, 2), strides=(2, 2), padding='same')(conv6)
    # up7 = Conv2D(base_filter_num*4, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv6))
    merge7 = concatenate([conv3,up7], axis = -1)
    conv7 = Conv2D(base_filter_num*4, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge7)
    conv7 = Conv2D(base_filter_num*4, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv7)

    up8 = Conv2DTranspose(base_filter_num*2, (2, 2), strides=(2, 2), padding='same')(conv7)
    # up8 = Conv2D(base_filter_num*2, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv7))
    merge8 = concatenate([conv2,up8], axis = -1)
    conv8 = Conv2D(base_filter_num*2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge8)
    conv8 = Conv2D(base_filter_num*2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv8)

    up9 = Conv2DTranspose(base_filter_num, (2, 2), strides=(2, 2), padding='same')(conv8)
    # up9 = Conv2D(base_filter_num, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv8))
    merge9 = concatenate([conv1,up9], axis = -1)
    conv9 = Conv2D(base_filter_num, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge9)
    conv9 = Conv2D(base_filter_num, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    # 二分类任务
    conv10 = Conv2D(1, 1, activation = 'sigmoid')(conv9)
    
    model = Model(input = inputs, output = conv10)
	model.compile(optimizer=Adam(lr = 1e-4), loss='binary_crossentropy', metrics=['acc'])
	model.summary()
    return model

2.keras实现unet++

def unet_plus_plus(input_size = (512,512,3),base_filter_num=64):
    inputs = Input(input_size)
    conv0_0 = Conv2D(base_filter_num, 3, activation = 'relu', padding = 'same', kernel_initializer