基于bp算法的手写数字识别python代码
时间: 2024-06-09 11:01:51 浏览: 23
基于BP算法的手写数字识别是一种常见的机器学习任务。下面是一个简单的基于Python的手写数字识别代码示例:
```python
import numpy as np
# 定义sigmoid函数
def sigmoid(x):
return 1 / (1 + np.exp(-x))
# 定义神经网络类
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
self.W1 = np.random.randn(self.input_size, self.hidden_size)
self.W2 = np.random.randn(self.hidden_size, self.output_size)
def forward(self, X):
# 前向传播
self.z = np.dot(X, self.W1)
self.z2 = sigmoid(self.z)
self.z3 = np.dot(self.z2, self.W2)
y_hat = sigmoid(self.z3)
return y_hat
def backward(self, X, y, y_hat, learning_rate):
# 反向传播
delta3 = (y_hat - y) * sigmoid(self.z3) * (1 - sigmoid(self.z3))
dW2 = np.dot(self.z2.T, delta3)
delta2 = np.dot(delta3, self.W2.T) * sigmoid(self.z2) * (1 - sigmoid(self.z2))
dW1 = np.dot(X.T, delta2)
# 更新权重
self.W1 -= learning_rate * dW1
self.W2 -= learning_rate * dW2
def train(self, X, y, epochs, learning_rate):
for i in range(epochs):
y_hat = self.forward(X)
self.backward(X, y, y_hat, learning_rate)
def predict(self, X):
y_hat = self.forward(X)
return np.argmax(y_hat, axis=1)
# 示例数据
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
y = np.array([[0], [1], [1], [0]])
# 创建神经网络对象
nn = NeuralNetwork(2, 4, 1)
# 训练神经网络
nn.train(X, y, epochs=10000, learning_rate=0.1)
# 预测结果
predictions = nn.predict(X)
print(predictions)
```
这段代码实现了一个简单的两层神经网络,使用BP算法进行训练和预测手写数字。其中,`X`是输入数据,`y`是对应的标签。通过调整参数和网络结构,可以提高识别准确率。