run_FCN.py 文件源码

def build_fcn(X):  
    #
    #   DESCRIPTION
    #       KERAS FCN DEFINITION
    #       Using the shape of the input to setup the input layer we create a FCN with 2 skips 
    #       
    #   INPUTS
    #       X [number_of_images, 400, 400, channels] 
    #
    #   OUTPUTS 
    #       model uninstantiated Keras model 
    #
    img_rows, img_cols = 400, 400
    inputs = Input(shape=X.shape[1:])
    conv1 = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(inputs)
    conv1 = Convolution2D(32, 4, 4, activation='relu', border_mode='same')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(conv1)

    conv2 = Convolution2D(64, 3, 3, activation='relu', border_mode='same')(pool1)
    conv2 = Convolution2D(64, 4, 4, activation='relu', border_mode='same')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2), strides=(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), strides=(2, 2))(conv3) # 50 50 

    conv4 = Convolution2D(256, 3, 3, activation='relu', border_mode='same')(pool3)
    conv4 = Convolution2D(256, 3, 3, activation='relu', border_mode='same')(conv4)
    conv4 = Convolution2D(256, 3, 3, activation='relu', border_mode='same')(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(conv4)  # 25 25

    conv5 = Convolution2D(512, 3, 3, activation='relu', border_mode='same')(pool4)
    conv5 = Convolution2D(512, 3, 3, activation='relu', border_mode='same')(conv5)
    conv5 = Convolution2D(512, 3, 3, activation='relu', border_mode='same')(conv5)
    pool5 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(conv5)  
    drop3 = Dropout(0.5)(pool5) 

    convpool3 = Convolution2D(60, 1, 1, activation='relu', border_mode='same')(pool3)
    convpool4 = Convolution2D(60, 1, 1, activation='relu', border_mode='same')(pool4)
    convdrop3 = Convolution2D(60, 1, 1, activation='relu', border_mode='same')(drop3)

    drop3x5 = UpSampling2D(size=(5, 5))(convdrop3)
    croppeddrop3x5 = Cropping2D(((5,5),(5,5)))(drop3x5) # 50 50
    pool4x2 = UpSampling2D(size=(2, 2))(convpool4) # 50 50
    fuse2 = merge([convpool3, pool4x2, croppeddrop3x5], mode='concat', concat_axis=-1) # 50 50 4224
    upscore3 = UpSampling2D(size=(8, 8))(fuse2) # F 8s 
    convscore3 = Convolution2D(1, 1, 1, activation='sigmoid')(upscore3)

    # Instantiate Model object 
    model = Model(input=inputs, output=convscore3)

    sgd = SGD(lr=1e-5, decay=2, momentum=0.9, nesterov=True)
    model.compile(optimizer=sgd, loss=pixel_wise_loss, metrics=['mean_squared_error'])  

    #model.compile(loss='mean_squared_error', optimizer=sgd)

    return model

## CUSTOM LOSS FUNCTION