利用python构建一个BP神经网络（附件为BP.py代码）并训练异或数据样本，并以图像形式呈现

好的，我会帮您解决这个问题。

首先，您需要准备以下数据：

import numpy as np

# 定义异或数据样本
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
y = np.array([[0], [1], [1], [0]])

然后，您需要构建一个BP神经网络。请参考如下代码：

class NeuralNetwork:
    def __init__(self, layers):
        self.layers = layers
        self.weights = []
        self.biases = []
        for i in range(len(layers) - 1):
            w = np.random.randn(layers[i], layers[i+1])
            b = np.random.randn(layers[i+1])
            self.weights.append(w)
            self.biases.append(b)
    
    def sigmoid(self, x):
        return 1 / (1 + np.exp(-x))
    
    def sigmoid_derivative(self, x):
        return x * (1 - x)
    
    def feedforward(self, x):
        a = x
        for w, b in zip(self.weights, self.biases):
            z = np.dot(a, w) + b
            a = self.sigmoid(z)
        return a
    
    def backpropagation(self, x, y, learning_rate):
        # 前向传递
        a = x
        activations = [a]
        zs = []
        for w, b in zip(self.weights, self.biases):
            z = np.dot(a, w) + b
            zs.append(z)
            a = self.sigmoid(z)
            activations.append(a)
        
        # 反向传递
        delta = (activations[-1] - y) * self.sigmoid_derivative(activations[-1])
        deltas = [delta]
        for i in range(len(self.layers)-2):
            delta = np.dot(deltas[-1], self.weights[-i-1].T) * self.sigmoid_derivative(activations[-2-i])
            deltas.append(delta)
        deltas.reverse()
        
        # 更新权重和偏差
        for i in range(len(self.weights)):
            w_grad = np.dot(activations[i].T, deltas[i])
            b_grad = np.sum(deltas[i], axis=0)
            self.weights[i] -= learning_rate * w_grad
            self.biases[i] -= learning_rate * b_grad
    
    def train(self, X, y, epochs, learning_rate):
        for i in range(epochs):
            for j in range(len(X)):
                self.backpropagation(X[j], y[j], learning_rate)

接下来，您需要实例化神经网络并进行训练。请参考如下代码：

# 实例化神经网络
nn = NeuralNetwork([2, 4, 1])

# 训练神经网络
nn.train(X, y, epochs=10000, learning_rate=0.1)

最后，您需要将训练后的结果可视化。请参考如下代码：

import matplotlib.pyplot as plt

# 可视化训练结果
x_min, x_max = -0.5, 1.5
y_min, y_max = -0.5, 1.5
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.01),
                     np.arange(y_min, y_max, 0.01))
Z = np.array([nn.feedforward(np.array([[x, y]]))[0][0] for x, y in np.c_[xx.ravel(), yy.ravel()]])
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, cmap=plt.cm.Spectral)
plt.scatter(X[:,0], X[:,1], c=y.ravel(), cmap=plt.cm.Spectral)
plt.show()

这样，您就可以看到训练结果了。完整代码如下：