基于BP神经网络的人脸识别代码

以下是基于BP神经网络的人脸识别代码：

import numpy as np
import cv2
import os
import random

# 加载训练数据
def load_data(data_folder):
    folders = os.listdir(data_folder)
    X = []
    y = []
    for folder in folders:
        files = os.listdir(os.path.join(data_folder, folder))
        for file in files:
            img = cv2.imread(os.path.join(data_folder, folder, file), cv2.IMREAD_GRAYSCALE)
            img = cv2.resize(img, (50, 50))
            X.append(img.reshape(-1))
            y.append(int(folder))
    return np.array(X), np.array(y)

# BP神经网络模型
class BPNeuralNetwork:
    def __init__(self, input_dim, hidden_dim, output_dim):
        self.input_dim = input_dim
        self.hidden_dim = hidden_dim
        self.output_dim = output_dim

        self.W1 = np.random.randn(input_dim, hidden_dim)
        self.b1 = np.zeros(hidden_dim)
        self.W2 = np.random.randn(hidden_dim, output_dim)
        self.b2 = np.zeros(output_dim)

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

    def forward(self, X):
        z1 = np.dot(X, self.W1) + self.b1
        a1 = self.sigmoid(z1)
        z2 = np.dot(a1, self.W2) + self.b2
        a2 = self.sigmoid(z2)
        return a2

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

    def backward(self, X, y, output):
        delta2 = (y - output) * self.sigmoid_derivative(output)
        delta1 = np.dot(delta2, self.W2.T) * self.sigmoid_derivative(self.sigmoid(np.dot(X, self.W1) + self.b1))

        dW2 = np.dot(self.sigmoid(np.dot(X, self.W1) + self.b1).T, delta2)
        db2 = np.sum(delta2, axis=0)
        dW1 = np.dot(X.T, delta1)
        db1 = np.sum(delta1, axis=0)

        self.W2 += dW2
        self.b2 += db2
        self.W1 += dW1
        self.b1 += db1

    def train(self, X, y, epochs=100):
        for i in range(epochs):
            for j in range(len(X)):
                output = self.forward(X[j])
                self.backward(X[j], np.eye(self.output_dim)[y[j]], output)

    def predict(self, X):
        return np.argmax(self.forward(X))

# 加载训练数据
X, y = load_data("data")

# 划分训练集和测试集
train_X = []
train_y = []
test_X = []
test_y = []
for i in range(len(X)):
    if random.random() < 0.8:
        train_X.append(X[i])
        train_y.append(y[i])
    else:
        test_X.append(X[i])
        test_y.append(y[i])

# 训练BP神经网络模型
model = BPNeuralNetwork(2500, 100, 5)
model.train(np.array(train_X), np.array(train_y))

# 在测试集上测试模型
correct = 0
for i in range(len(test_X)):
    if model.predict(test_X[i]) == test_y[i]:
        correct += 1
accuracy = correct / len(test_X)
print("Accuracy:", accuracy)

以上代码包括加载训练数据、BP神经网络模型、训练模型、测试模型等部分。其中，`load_data`函数用于加载训练数据，`BPNeuralNetwork`类定义了BP神经网络模型，包括前向传播、反向传播等方法，`train`方法用于训练模型，`predict`方法用于预测输出，最后通过计算准确率测试模型性能。