fly6516
99f9a797ba
- 将 BPNeuralNetwork 类从 NumPy 重新实现为 PyTorch 模型 - 使用 PyTorch 的自动求导和优化器替换手动反向传播和权重更新 - 将数据转换为 PyTorch 张量并支持 GPU 加速 -保留了原始代码的基本结构和功能
88 lines
3.4 KiB
Python
88 lines
3.4 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
import torch.optim as optim
|
|
from ucimlrepo import fetch_ucirepo
|
|
from sklearn.model_selection import KFold
|
|
from sklearn.metrics import accuracy_score
|
|
from sklearn.preprocessing import StandardScaler
|
|
import numpy as np
|
|
|
|
# 定义BP神经网络类
|
|
class BPNeuralNetwork(nn.Module):
|
|
def __init__(self, input_size, hidden_size, output_size):
|
|
super(BPNeuralNetwork, self).__init__()
|
|
# 初始化输入层、隐藏层和输出层的大小
|
|
self.input_size = input_size
|
|
self.hidden_size = hidden_size
|
|
self.output_size = output_size
|
|
|
|
# 初始化权重和偏置
|
|
self.fc1 = torch.nn.Linear(self.input_size, self.hidden_size) # 输入层到隐藏层的全连接层
|
|
self.fc2 = torch.nn.Linear(self.hidden_size, self.output_size) # 隐藏层到输出层的全连接层
|
|
|
|
def forward(self, x):
|
|
# 前向传播
|
|
x = torch.sigmoid(self.fc1(x)) # 隐藏层的输出
|
|
x = torch.sigmoid(self.fc2(x)) # 输出层的输出
|
|
return x
|
|
|
|
# 将标签转换为one-hot编码
|
|
def one_hot_encode(y):
|
|
# 确保 y 中的每个元素是字符串
|
|
y = np.array([str(label) for label in y])
|
|
# 创建一个标签到整数的映射
|
|
label_to_int = {label: i for i, label in enumerate(np.unique(y))}
|
|
# 将标签转换为整数
|
|
y_int = np.array([label_to_int[label] for label in y])
|
|
n_values = np.max(y_int) + 1
|
|
return torch.eye(n_values)[y_int] # 返回one-hot编码
|
|
|
|
# fetch dataset
|
|
wine_quality = fetch_ucirepo(id=186)
|
|
|
|
# data (as pandas dataframes)
|
|
X = wine_quality.data.features.values # 特征数据
|
|
y = wine_quality.data.targets.values # 标签数据
|
|
|
|
# 特征缩放
|
|
scaler = StandardScaler()
|
|
X = scaler.fit_transform(X) # 标准化特征数据
|
|
|
|
# 对标签进行one-hot编码
|
|
y_encoded = one_hot_encode(y)
|
|
|
|
# 将数据转换为PyTorch张量并移至GPU
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
X = torch.tensor(X, dtype=torch.float32).to(device)
|
|
y_encoded = y_encoded.to(device)
|
|
|
|
# 十折交叉验证
|
|
kf = KFold(n_splits=10, shuffle=True, random_state=42)
|
|
accuracies = []
|
|
|
|
for train_index, test_index in kf.split(X):
|
|
X_train, X_test = X[train_index], X[test_index] # 训练集和测试集的特征数据
|
|
y_train, y_test = y_encoded[train_index], y_encoded[test_index] # 训练集和测试集的标签数据
|
|
|
|
# 创建并训练BP神经网络
|
|
nn = BPNeuralNetwork(input_size=X_train.shape[1], hidden_size=20, output_size=y_train.shape[1]).to(device) # 修改隐藏层大小
|
|
criterion = torch.nn.MSELoss() # 使用均方误差损失函数
|
|
optimizer = optim.SGD(nn.parameters(), lr=0.0001) # 使用随机梯度下降优化器
|
|
|
|
for epoch in range(50000): # 增加训练轮数
|
|
optimizer.zero_grad() # 清零梯度
|
|
output = nn(X_train) # 前向传播
|
|
loss = criterion(output, y_train) # 计算损失
|
|
loss.backward() # 反向传播
|
|
optimizer.step() # 更新权重和偏置
|
|
|
|
if epoch % 1000 == 0:
|
|
print(f'Epoch {epoch}, Loss: {loss.item()}') # 打印损失
|
|
|
|
# 预测并计算准确率
|
|
with torch.no_grad():
|
|
predictions = nn(X_test)
|
|
accuracy = accuracy_score(torch.argmax(y_test, dim=1).cpu().numpy(), torch.argmax(predictions, dim=1).cpu().numpy()) # 计算准确率
|
|
accuracies.append(accuracy) # 存储每次交叉验证的准确率
|
|
|
|
print(f'Average Accuracy: {np.mean(accuracies)}') # 打印平均准确率 |