Python 我得到了&x201C；缩进错误：应为缩进块”；在np.random.seed（2）中。如何解决这个问题？

但出现以下错误： 文件“”，第4行 np.random.seed（2）#我们设置了一个seed，以便我们的输出与我们的匹配，尽管初始化是随机的。 ^ 缩进错误：应为缩进块，包括以下内容：

import numpy as np
def initialize_parameters(n_x, n_h, n_y):

    np.random.seed(2) # we set up a seed so that our output matches ours although the initialization is random.

    W1 = np.random.randn(n_h, n_x) * 0.01 #weight matrix of shape (n_h, n_x)
    b1 = np.zeros(shape=(n_h, 1))  #bias vector of shape (n_h, 1)
    W2 = np.random.randn(n_y, n_h) * 0.01   #weight matrix of shape (n_y, n_h)
    b2 = np.zeros(shape=(n_y, 1))  #bias vector of shape (n_y, 1)

    #store parameters into a dictionary    
    parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2}

    return parameters

#Function to define the size of the layer
def layer_sizes(X, Y):
    n_x = X.shape[0] # size of input layer
    n_h = 6# size of hidden layer
    n_y = Y.shape[0] # size of output layer
    return (n_x, n_h, n_y)

到

在上面的示例中，需要缩进四个空格。即：

return parameters

格式应如下所示：

def initialize_parameters(n_x, n_h, n_y):

np.random.seed(2) # we set up a seed so that our output matches ours although the initialization is random.

W1 = np.random.randn(n_h, n_x) * 0.01 #weight matrix of shape (n_h, n_x)
b1 = np.zeros(shape=(n_h, 1))  #bias vector of shape (n_h, 1)
W2 = np.random.randn(n_y, n_h) * 0.01   #weight matrix of shape (n_y, n_h)
b2 = np.zeros(shape=(n_y, 1))  #bias vector of shape (n_y, 1)

#store parameters into a dictionary    
parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2}

return parameters

---

（我额外添加了

参数

字典格式；）

函数中应该包含的代码需要缩进。这就是python如何知道属于函数的代码的原因。我在您的文章中编辑了函数的缩进方式。只需确保函数/类等内部的内容正确缩进您声明了一个函数行2，因此您必须缩进属于此函数的行。如果函数应该是空的，那么现在您只需添加一个“path”作为body@Chrispresso这应该是评论或回答，而不是对问题的编辑。以这种方式编辑只会导致提问者、评论者和答案之间的混淆

def initialize_parameters(n_x, n_h, n_y):

np.random.seed(2) # we set up a seed so that our output matches ours although the initialization is random.

W1 = np.random.randn(n_h, n_x) * 0.01 #weight matrix of shape (n_h, n_x)
b1 = np.zeros(shape=(n_h, 1))  #bias vector of shape (n_h, 1)
W2 = np.random.randn(n_y, n_h) * 0.01   #weight matrix of shape (n_y, n_h)
b2 = np.zeros(shape=(n_y, 1))  #bias vector of shape (n_y, 1)

#store parameters into a dictionary    
parameters = {"W1": W1,
                  "b1": b1,
                  "W2": W2,
                  "b2": b2}

return parameters

def initialize_parameters(n_x, n_h, n_y):

    np.random.seed(2) # we set up a seed so that our output matches ours although the initialization is random.

    W1 = np.random.randn(n_h, n_x) * 0.01 #weight matrix of shape (n_h, n_x)
    b1 = np.zeros(shape=(n_h, 1))  #bias vector of shape (n_h, 1)
    W2 = np.random.randn(n_y, n_h) * 0.01   #weight matrix of shape (n_y, n_h)
    b2 = np.zeros(shape=(n_y, 1))  #bias vector of shape (n_y, 1)

    #store parameters into a dictionary    
    parameters = {
        "W1": W1,
        "b1": b1,
        "W2": W2,
        "b2": b2
    }

    return parameters