深圳 汽车网站建设江苏省建设考试信息管理系统网站
知识点回顾：
- PyTorch和cuda的安装
- 查看显卡信息的命令行命令（cmd中使用）
- cuda的检查
- 简单神经网络的流程
- 数据预处理（归一化、转换成张量）
- 模型的定义
- 继承nn.Module类
- 定义每一个层
- 定义前向传播流程
- 定义损失函数和优化器
- 定义训练流程
- 可视化loss过程
-
# test_pytorch.py import torch# 检查导入是否成功 print(f"PyTorch版本: {torch.__version__}") print(f"CUDA可用: {torch.cuda.is_available()}")# 设置随机种子 torch.manual_seed(42)# 创建一个张量测试 x = torch.randn(5, 5) print(f"随机张量:\n{x}") import torch.nn as nn import torch.optim as optim from torch.utils.data import DataLoader, TensorDataset import numpy as np import matplotlib.pyplot as plt# 设置随机种子确保结果可复现 torch.manual_seed(42) np.random.seed(42)# ------------------------- # 1. 环境检查 # ------------------------- def check_environment():"""检查CUDA可用性并打印环境信息"""if torch.cuda.is_available():print(f"CUDA可用 - 设备: {torch.cuda.get_device_name(0)}")print(f"CUDA版本: {torch.version.cuda}")else:print("CUDA不可用，将使用CPU进行计算")print(f"PyTorch版本: {torch.__version__}")# ------------------------- # 2. 数据预处理 # ------------------------- class DataPreprocessor:"""数据预处理类，支持回归和分类任务"""def __init__(self, task_type="regression"):"""task_type: 'regression' 或 'classification'"""self.task_type = task_typeself.x_mean, self.x_std = None, Noneself.y_mean, self.y_std = None, Nonedef preprocess(self, x, y):"""预处理数据并转换为张量"""# 特征归一化self.x_mean, self.x_std = x.mean(), x.std()x_normalized = (x - self.x_mean) / self.x_std# 根据任务类型处理标签if self.task_type == "regression":self.y_mean, self.y_std = y.mean(), y.std()y_normalized = (y - self.y_mean) / self.y_stdy_tensor = torch.tensor(y_normalized, dtype=torch.float32).view(-1, 1)else: # 分类任务y_tensor = torch.tensor(y, dtype=torch.long)x_tensor = torch.tensor(x_normalized, dtype=torch.float32).view(-1, 1)return x_tensor, y_tensordef denormalize_prediction(self, pred):"""将预测结果反归一化（仅用于回归任务）"""if self.task_type == "regression":return pred * self.y_std + self.y_meanreturn pred# ------------------------- # 3. 模型定义 # ------------------------- class SimpleNet(nn.Module):"""简单的两层神经网络"""def __init__(self, input_size=1, hidden_size=10, output_size=1):super(SimpleNet, self).__init__()self.fc1 = nn.Linear(input_size, hidden_size)self.relu = nn.ReLU()self.fc2 = nn.Linear(hidden_size, output_size)def forward(self, x):x = self.fc1(x)x = self.relu(x)x = self.fc2(x)return x# ------------------------- # 4. 训练模块 # ------------------------- class Trainer:"""模型训练器"""def __init__(self, model, task_type="regression", lr=0.01):self.model = modelself.task_type = task_type# 根据任务类型选择损失函数self.criterion = nn.MSELoss() if task_type == "regression" else nn.CrossEntropyLoss()self.optimizer = optim.Adam(model.parameters(), lr=lr)self.train_losses = []def train(self, dataloader, num_epochs=100, print_every=10):"""训练模型并记录损失"""for epoch in range(num_epochs):epoch_loss = 0.0for inputs, targets in dataloader:# 前向传播outputs = self.model(inputs)loss = self.criterion(outputs, targets)# 反向传播和优化self.optimizer.zero_grad()loss.backward()self.optimizer.step()epoch_loss += loss.item()# 记录每个epoch的平均损失avg_loss = epoch_loss / len(dataloader)self.train_losses.append(avg_loss)if (epoch + 1) % print_every == 0:print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {avg_loss:.4f}')return self.train_lossesdef plot_loss(self):"""可视化训练损失"""plt.figure(figsize=(10, 6))plt.plot(range(1, len(self.train_losses) + 1), self.train_losses, label='Training Loss')plt.xlabel('Epoch')plt.ylabel('Loss')plt.title('Training Loss over Epochs')plt.legend()plt.grid(True)plt.show()# ------------------------- # 5. 主函数 # ------------------------- def main():# 检查环境check_environment()# 生成示例数据task_type = "regression" # 或 "classification"if task_type == "regression":# 回归任务数据x = np.linspace(0, 10, 100)y = 2 * x + 1 + np.random.randn(100) * 0.5 # y = 2x + 1 + 噪声else:# 分类任务数据x = np.linspace(0, 10, 100)y = (x > 5).astype(int) # 二分类问题# 数据预处理preprocessor = DataPreprocessor(task_type)x_tensor, y_tensor = preprocessor.preprocess(x, y)# 创建数据加载器dataset = TensorDataset(x_tensor, y_tensor)dataloader = DataLoader(dataset, batch_size=16, shuffle=True)# 初始化模型if task_type == "regression":model = SimpleNet(input_size=1, output_size=1)else:model = SimpleNet(input_size=1, output_size=2) # 二分类问题有2个类别# 训练模型trainer = Trainer(model, task_type=task_type, lr=0.01)losses = trainer.train(dataloader, num_epochs=100)# 可视化损失trainer.plot_loss()# 评估模型model.eval()with torch.no_grad():test_x = np.array([5.0]) # 测试输入test_x_normalized = (test_x - preprocessor.x_mean) / preprocessor.x_stdtest_tensor = torch.tensor(test_x_normalized, dtype=torch.float32).view(-1, 1)prediction = model(test_tensor)if task_type == "regression":# 反归一化回归预测结果prediction = preprocessor.denormalize_prediction(prediction.item())print(f"回归预测结果: {prediction:.4f}")print(f"真实值: {2*test_x[0] + 1:.4f}") # 基于y=2x+1else:# 获取分类预测结果_, predicted = torch.max(prediction, 1)print(f"分类预测类别: {predicted.item()}")print(f"真实类别: {1 if test_x[0] > 5 else 0}")if __name__ == "__main__":main()