python 的語法定義和C++、matlab、java 還是很有區(qū)別的。

1. 括號(hào)與函數(shù)調(diào)用

def devided_3(x):return x/3.print(a) #不帶括號(hào)調(diào)用的結(jié)果：<function a at 0x139c756a8> print(a(3)) #帶括號(hào)調(diào)用的結(jié)果：1

不帶括號(hào)時(shí)，調(diào)用的是函數(shù)在內(nèi)存在的首地址； 帶括號(hào)時(shí)，調(diào)用的是函數(shù)在內(nèi)存區(qū)的代碼塊，輸入?yún)?shù)后執(zhí)行函數(shù)體。

2. 括號(hào)與類調(diào)用

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(nèi)容：this is out of __init__()x = test() # 類的實(shí)例化 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 funcfunc(2018)(11)>>> this is func with another func as return2018this is another function11

其實(shí)，這種情況最常用在卷積神經(jīng)網(wǎng)絡(luò)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 zeroesX = ZeroPadding2D((3, 3))(X_input)# CONV -> BN -> RELU Block applied to XX = Conv2D(32, (7, 7), strides = (1, 1), name = 'conv0')(X)X = BatchNormalization(axis = 3, name = 'bn0')(X)X = Activation('relu')(X)# MAXPOOLX = MaxPooling2D((2, 2), name='max_pool')(X)# FLATTEN X (means convert it to a vector) + FULLYCONNECTEDX = 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

?

與50位技術(shù)專家面對(duì)面20年技術(shù)見證，附贈(zèng)技術(shù)全景圖

總結(jié)

以上是生活随笔為你收集整理的Python 中 function(#) (X)格式 和 (#)在Python3.*中的注意的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。