python 的語法定義和C++、matlab、java 還是很有區別的。

1. 括號與函式呼叫

def devided_3(x):
      return x/3.
 
print(a)    #不帶括號呼叫的結果：<function a at 0x139c756a8>
print(a(3)) #帶括號呼叫的結果：1

不帶括號時，呼叫的是函式在記憶體在的首地址； 帶括號時，呼叫的是函式在記憶體區的程式碼塊，輸入引數後執行函式體。

2. 括號與類呼叫

class test():
    y = 'this is out of __init__()'
    def __init__(self):
        self.y = 'this is in the __init__()'

x = test    # x是類位置的首地址
print(x.y)  # 輸出類的內容：this is out of __init__()

x = test()  # 類的例項化
print(x.y)  # 輸出類的屬性：this is in the __init__() ; 
 

3. function(#) (input)

def With_func_rtn(a):
    print("this is func with another func as return")
    print(a)
    def func(b):
        print("this is another function")
        print(b)
    return func
 
func(2018)(11)

>>> this is func with another func as return
    2018
    this is another function
    11
 

其實，這種情況最常用在卷積神經網路中：

def model(input_shape):
    # Define the input placeholder as a tensor with shape input_shape.
    X_input = Input(input_shape)
 
    # Zero-Padding: pads the border of X_input with zeroes
    X = ZeroPadding2D((3, 3))(X_input)
 
    # CONV -> BN -> RELU Block applied to X
    X = Conv2D(32, (7, 7), strides = (1, 1), name = 'conv0')(X)
    X = BatchNormalization(axis = 3, name = 'bn0')(X)
    X = Activation('relu')(X)
 
    # MAXPOOL
    X = MaxPooling2D((2, 2), name='max_pool')(X)
 
    # FLATTEN X (means convert it to a vector) + FULLYCONNECTED
    X = Flatten()(X)
    X = Dense(1, activation='sigmoid', name='fc')(X)
 
    # Create model. This creates your Keras model instance, you'll use this instance to train/test the model.
    model = Model(inputs = X_input, outputs = X, name='HappyModel')
 
    return model