当前位置：首页 > news >正文

Day 40训练

news 2025/6/6 11:57:34

Day 40 训练

PyTorch 图像数据训练与测试的规范写法
- 单通道图像的规范训练流程
- - 数据预处理与加载
  - 模型定义
  - 训练与测试函数封装
  - 模型训练执行
- 彩色图像的扩展应用
- - 数据预处理调整
  - 模型结构调整
- 关键要点总结

知识点回顾：

彩色和灰度图片测试和训练的规范写法：封装在函数中
展平操作：除第一个维度batchsize外全部展平
dropout操作：训练阶段随机丢弃神经元，测试阶段eval模式关闭dropout

作业：仔细学习下测试和训练代码的逻辑，这是基础，这个代码框架后续会一直沿用，后续的重点慢慢就是转向模型定义阶段了。

PyTorch 图像数据训练与测试的规范写法

在深度学习项目中，规范的代码结构能极大提升开发效率与代码可维护性。本文将基于 PyTorch 框架，详细讲解图像数据训练和测试的规范写法，从单通道图像到彩色图像，助你构建高效、清晰的模型训练流程。

单通道图像的规范训练流程

数据预处理与加载

我们以 MNIST 手写数字数据集为例，其为单通道灰度图像。数据预处理是模型训练的起点，我们利用 torchvision.transforms 对图像进行转换：

transform = transforms.Compose([transforms.ToTensor(),  # 转换为张量并归一化到[0,1]transforms.Normalize((0.1307,), (0.3081,))  # 使用 MNIST 数据集的均值和标准差进行标准化
])

接着加载数据集并创建数据加载器：

train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST(root='./data', train=False, transform=transform)batch_size = 64
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

模型定义

针对 MNIST 图像尺寸（28×28），定义一个多层感知机（MLP）模型：

class MLP(nn.Module):def __init__(self):super(MLP, self).__init__()self.flatten = nn.Flatten()  # 将 28x28 图像展平为 784 维向量self.layer1 = nn.Linear(784, 128)self.relu = nn.ReLU()self.layer2 = nn.Linear(128, 10)def forward(self, x):x = self.flatten(x)x = self.layer1(x)x = self.relu(x)x = self.layer2(x)return x

训练与测试函数封装

为提升代码复用性与可读性，我们将训练和测试逻辑封装为函数：

def train(model, train_loader, test_loader, criterion, optimizer, device, epochs):model.train()all_iter_losses = []iter_indices = []for epoch in range(epochs):running_loss = 0.0correct = 0total = 0for batch_idx, (data, target) in enumerate(train_loader):data, target = data.to(device), target.to(device)optimizer.zero_grad()output = model(data)loss = criterion(output, target)loss.backward()optimizer.step()iter_loss = loss.item()all_iter_losses.append(iter_loss)iter_indices.append(epoch * len(train_loader) + batch_idx + 1)running_loss += iter_loss_, predicted = output.max(1)total += target.size(0)correct += predicted.eq(target).sum().item()if (batch_idx + 1) % 100 == 0:print(f'Epoch: {epoch+1}/{epochs} | Batch: {batch_idx+1}/{len(train_loader)} 'f'| 单 Batch 损失: {iter_loss:.4f} | 累计平均损失: {running_loss/(batch_idx+1):.4f}')epoch_train_loss = running_loss / len(train_loader)epoch_train_acc = 100. * correct / totalepoch_test_loss, epoch_test_acc = test(model, test_loader, criterion, device)print(f'Epoch {epoch+1}/{epochs} 完成 | 训练准确率: {epoch_train_acc:.2f}% | 测试准确率: {epoch_test_acc:.2f}%')plot_iter_losses(all_iter_losses, iter_indices)return epoch_test_accdef test(model, test_loader, criterion, device):model.eval()test_loss = 0correct = 0total = 0with torch.no_grad():for data, target in test_loader:data, target = data.to(device), target.to(device)output = model(data)test_loss += criterion(output, target).item()_, predicted = output.max(1)total += target.size(0)correct += predicted.eq(target).sum().item()avg_loss = test_loss / len(test_loader)accuracy = 100. * correct / totalreturn avg_loss, accuracy

模型训练执行

设置训练轮次并启动训练：

epochs = 2
print("开始训练模型...")
final_accuracy = train(model, train_loader, test_loader, criterion, optimizer, device, epochs)
print(f"训练完成！最终测试准确率: {final_accuracy:.2f}%")

彩色图像的扩展应用

对于彩色图像（如 CIFAR-10 数据集），处理流程与单通道图像类似，主要差异在于：

数据预处理调整

transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))  # 适应彩色图像的标准化
])

模型结构调整

class MLP(nn.Module):def __init__(self):super(MLP, self).__init__()self.flatten = nn.Flatten()  # 将 3x32x32 图像展平为 3072 维向量self.layer1 = nn.Linear(3072, 512)self.relu1 = nn.ReLU()self.dropout1 = nn.Dropout(0.2)self.layer2 = nn.Linear(512, 256)self.relu2 = nn.ReLU()self.dropout2 = nn.Dropout(0.2)self.layer3 = nn.Linear(256, 10)def forward(self, x):x = self.flatten(x)x = self.layer1(x)x = self.relu1(x)x = self.dropout1(x)x = self.layer2(x)x = self.relu2(x)x = self.dropout2(x)x = self.layer3(x)return x