BP神经网络（Python代码实现）不使用pytorch

你可以使用NumPy库来实现一个简单的反向传播神经网络（BP神经网络）的Python代码。下面是一个基本的代码示例：

import numpy as np

# 定义激活函数sigmoid
def sigmoid(x):
    return 1 / (1 + np.exp(-x))

# 定义激活函数sigmoid的导数，用于反向传播
def sigmoid_derivative(x):
    return x * (1 - x)

# 定义BP神经网络类
class NeuralNetwork:
    def __init__(self, input_size, hidden_size, output_size):
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.output_size = output_size
        
        # 初始化权重和偏置
        self.weights1 = np.random.randn(self.input_size, self.hidden_size)
        self.bias1 = np.zeros((1, self.hidden_size))
        self.weights2 = np.random.randn(self.hidden_size, self.output_size)
        self.bias2 = np.zeros((1, self.output_size))
        
    def forward(self, X):
        # 前向传播
        self.z1 = np.dot(X, self.weights1) + self.bias1
        self.a1 = sigmoid(self.z1)
        self.z2 = np.dot(self.a1, self.weights2) + self.bias2
        self.a2 = sigmoid(self.z2)
        return self.a2
    
    def backward(self, X, y, output):
        # 反向传播
        self.error = y - output
        self.delta2 = self.error * sigmoid_derivative(output)
        self.error_hidden = np.dot(self.delta2, self.weights2.T)
        self.delta1 = self.error_hidden * sigmoid_derivative(self.a1)
        
        # 更新权重和偏置
        self.weights2 += np.dot(self.a1.T, self.delta2)
        self.bias2 += np.sum(self.delta2, axis=0, keepdims=True)
        self.weights1 += np.dot(X.T, self.delta1)
        self.bias1 += np.sum(self.delta1, axis=0)
        
    def train(self, X, y, epochs):
        for epoch in range(epochs):
            # 前向传播
            output = self.forward(X)
            
            # 反向传播
            self.backward(X, y, output)
            
    def predict(self, X):
        # 预测
        return self.forward(X)

# 创建训练数据集
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
y = np.array([[0], [1], [1], [0]])

# 创建BP神经网络对象
nn = NeuralNetwork(input_size=2, hidden_size=3, output_size=1)

# 训练BP神经网络
nn.train(X, y, epochs=10000)

# 预测新样本
new_X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
predictions = nn.predict(new_X)

print(predictions)

这段代码实现了一个简单的逻辑门XOR的BP神经网络。它使用了NumPy库来进行矩阵运算和数学函数计算。你可以根据自己的需要修改网络结构、训练数据和训练参数。希望能对你有所帮助！