python - 我在 np.random.seed(2) 中得到 “IndentationError: expected an indented block”。如何解决这个问题？

Question

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)

但出现此错误: 文件“”，第 4 行 np.random.seed(2) # 我们设置了一个种子，以便我们的输出与我们的输出匹配，尽管初始化是随机的。 ^IndentationError:需要一个缩进 block

Answer 1

一切来自:

def initialize_parameters(n_x, n_h, n_y):

到

return parameters

在上面的示例中需要缩进四个空格。即，这个:

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

应采用如下格式:

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

(我加入了 parameters 字典格式作为奖励；))