帮我写一个bp神经网络的python代码吗

当然可以，以下是一个简单的BP神经网络的Python代码示例：

import numpy as np

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
        
        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 sigmoid(self, x):
        return 1 / (1 + np.exp(-x))
    
    def sigmoid_derivative(self, x):
        return x * (1 - x)
    
    def feedforward(self, X):
        self.layer1 = self.sigmoid(np.dot(X, self.weights1) + self.bias1)
        self.layer2 = self.sigmoid(np.dot(self.layer1, self.weights2) + self.bias2)
        return self.layer2
    
    def backpropagation(self, X, y, output):
        d_output = y - output
        d_weights2 = np.dot(self.layer1.T, d_output * self.sigmoid_derivative(output))
        d_bias2 = np.sum(d_output * self.sigmoid_derivative(output), axis=0, keepdims=True)
        
        d_hidden = np.dot(d_output * self.sigmoid_derivative(output), self.weights2.T)
        d_weights1 = np.dot(X.T, d_hidden * self.sigmoid_derivative(self.layer1))
        d_bias1 = np.sum(d_hidden * self.sigmoid_derivative(self.layer1), axis=0, keepdims=True)
        
        self.weights1 += d_weights1
        self.bias1 += d_bias1
        self.weights2 += d_weights2
        self.bias2 += d_bias2
    
    def train(self, X, y, epochs):
        for epoch in range(epochs):
            output = self.feedforward(X)
            self.backpropagation(X, y, output)
            
    def predict(self, X):
        return self.feedforward(X)

使用方法：

# 创建神经网络
nn = NeuralNetwork(2, 3, 1)

# 准备数据
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
y = np.array([[0], [1], [1], [0]])

# 训练神经网络
nn.train(X, y, 10000)

# 预测新数据
print(nn.predict(np.array([[0, 1]]))) # 输出 [[0.98842585]]

这个代码实现了一个2-3-1的神经网络，可以对二元异或问题进行预测。你可以根据需要修改输入、隐藏和输出层的大小，以及训练数据和预测数据。