Python 神经网络类can'；无法访问其属性

我已经练习了以下简单的代码

import numpy as np


class NeuralNetwork():
    def _init_(self):
        np.random.seed(1)
        # generating numbers between [-1 1]
        self.synaptic_weights = 2 * np.random.random((3, 1))-1

    def sigmoid(self, x):
         return 1/(1 + np.exp(-x))

    def sigmoid_derivative(self, x):
          return x * (1 - x)

    def think(self, inputs):
          inputs=inputs.astype(float)
          output = self.sigmoid(np.product(inputs,self.synaptic_weights))
          return  output

    def train(self,training_inputs,training_outputs,training_iterations):
           for iteration in range(training_iterations):
               output = self.think(training_inputs)
               error = training_outputs - output
               adjustment =np.dot(training_inputs.T, error * self.sigmoid_derivative(output))
               self.synaptic_weights += adjustment


if __name__ == "__main__":
    # initializing the neuron class
    neural_network = NeuralNetwork()

    print("Beginning Randomly Generated Weights: ")
    print(neural_network.synaptic_weights)
    # training data consisting of 4 examples--3 input values and 1 output
    training_inputs = np.array([[0, 0, 1],
                                [1, 1, 1],
                                [1, 0, 1],
                                [0, 1, 1]])

    training_outputs = np.array([[0, 1, 1, 0]]).T

    # training taking place
    neural_network.train(training_inputs, training_outputs, 15000)

    print("Ending Weights After Training: ")
    print(neural_network.synaptic_weights)

    user_input_one = str(input("User Input One: "))
    user_input_two = str(input("User Input Two: "))
    user_input_three = str(input("User Input Three: "))

    print("Considering New Situation: ", user_input_one, user_input_two, user_input_three)
    print("New Output data: ")
    print(neural_network.think(np.array([user_input_one, user_input_two, user_input_three])))
    print("Wow, we did it!")

但当我运行它时，它给了我以下错误：

Traceback (most recent call last):
Beginning Randomly Generated Weights: 
  File "I:/scientific_python/deep_learning_machine_learning/deep_learning.py", line 34, in <module>
    print(neural_network.synaptic_weights)
AttributeError: 'NeuralNetwork' object has no attribute 'synaptic_weights'

Process finished with exit code 1

回溯（最近一次呼叫最后一次）：
开始随机生成的权重：
文件“I:/scientific\u python/deep\u learning\u machine\u learning/deep\u learning.py”，第34行，在
打印（神经网络、突触权重）
AttributeError:“NeuralNetwork”对象没有属性“synaptic_权重”
进程已完成，退出代码为1

我不明白为什么？在NeuralNetwork（）类中，我已经完成了synaptic_权重的初始化，所以为什么类无法访问？提前感谢示例代码片段：

class A:
    def __init__(self):
        self.test = 0
a = A()
print(a.test)

---

检查init方法的定义，方法名称应该是

\uuuu init\uuuu

您的代码有两个问题：

\u init\uu

函数需要双下划线

其次，可以使用

np.dot

代替

np.product

将权重与输入矩阵相乘

以下是工作代码：

import numpy as np


class NeuralNetwork():
    def __init__(self):
        np.random.seed(1)
        # generating numbers between [-1 1]
        self.synaptic_weights = 2 * np.random.random((3, 1))-1

    def sigmoid(self, x):
         return 1/(1 + np.exp(-x))

    def sigmoid_derivative(self, x):
          return x * (1 - x)

    def think(self, inputs):
          inputs=inputs.astype(float)
          output = self.sigmoid(np.dot(inputs,self.synaptic_weights))
          return  output

    def train(self,training_inputs,training_outputs,training_iterations):
           for iteration in range(training_iterations):
               output = self.think(training_inputs)
               error = training_outputs - output
               adjustment =np.dot(training_inputs.T, error * self.sigmoid_derivative(output))
               self.synaptic_weights += adjustment


if __name__ == "__main__":
    # initializing the neuron class
    neural_network = NeuralNetwork()

    print("Beginning Randomly Generated Weights: ")
    print(neural_network.synaptic_weights)
    # training data consisting of 4 examples--3 input values and 1 output
    training_inputs = np.array([[0, 0, 1],
                                [1, 1, 1],
                                [1, 0, 1],
                                [0, 1, 1]])

    training_outputs = np.array([[0, 1, 1, 0]]).T

    # training taking place
    neural_network.train(training_inputs, training_outputs, 15000)

    print("Ending Weights After Training: ")
    print(neural_network.synaptic_weights)

    user_input_one = str(input("User Input One: "))
    user_input_two = str(input("User Input Two: "))
    user_input_three = str(input("User Input Three: "))

    print("Considering New Situation: ", user_input_one, user_input_two, user_input_three)
    print("New Output data: ")
    print(neural_network.think(np.array([user_input_one, user_input_two, user_input_three])))
    print("Wow, we did it!")

---

我认为您缺少了

\u init\u

函数中的双下划线。谢谢，这个问题怎么样？TypeError:只有整数标量数组可以转换为标量索引关于这个问题，请检查@user2314737 answer为什么我应该使用点？@datodatuashvili您必须考虑：您的输入代表什么？由于是

think

中的代码逐行执行矩阵乘法，也就是说，对于输入矩阵中的每一行，它会生成行中元素与权重列的线性组合。这个组合是一个数字。进行反向传播时，调整权重以获得更好的数字。因此基本上，

输入

矩阵每行包含一个示例（一个示例用于训练网络=一维向量）。