Pytorch、CNN解読の核心ポイントを徹底分析！

import torchimport torch.nn as nnimport torch.optim as optimfrom torchvision import datasets, transforms# 定义卷积神经网络类class SimpleCNN(nn.Module):def __init__(self):super(SimpleCNN, self).__init__()# 卷积层1self.conv1 = nn.Conv2d(in_channels=1, out_channels=16, kernel_size=3, stride=1, padding=1)self.relu = nn.ReLU()self.pool = nn.MaxPool2d(kernel_size=2, stride=2)# 卷积层2self.conv2 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3, stride=1, padding=1)# 全连接层self.fc1 = nn.Linear(32 * 7 * 7, 10)# 输入大小根据数据调整def forward(self, x):x = self.conv1(x)x = self.relu(x)x = self.pool(x)x = self.conv2(x)x = self.relu(x)x = self.pool(x)x = x.view(-1, 32 * 7 * 7)x = self.fc1(x)return x# 定义损失函数和优化器net = SimpleCNN()criterion = nn.CrossEntropyLoss()optimizer = optim.Adam(net.parameters(), lr=0.001)# 加载和预处理数据transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=64, shuffle=True)# 训练网络num_epochs = 5for epoch in range(num_epochs):for i, (images, labels) in enumerate(train_loader):optimizer.zero_grad()outputs = net(images)loss = criterion(outputs, labels)loss.backward()optimizer.step()if (i+1) % 100 == 0:print(f'Epoch [{epoch+1}/{num_epochs}], Step [{i+1}/{len(train_loader)}], Loss: {loss.item()}')# 测试网络net.eval()with torch.no_grad():correct = 0total = 0for images, labels in test_loader:outputs = net(images)_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()accuracy = correct / totalprint('Accuracy on the test set: {}%'.format(100 * accuracy))

import matplotlib.pyplot as plt

# 在训练循环中添加以下代码train_loss_list = []accuracy_list = []for epoch in range(num_epochs):running_loss = 0.0correct = 0total = 0for i, (images, labels) in enumerate(train_loader):optimizer.zero_grad()outputs = net(images)loss = criterion(outputs, labels)loss.backward()optimizer.step()running_loss += loss.item()_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()if (i+1) % 100 == 0:print(f'Epoch [{epoch+1}/{num_epochs}], Step [{i+1}/{len(train_loader)}], Loss: {loss.item()}')epoch_loss = running_loss / len(train_loader)accuracy = correct / totaltrain_loss_list.append(epoch_loss)accuracy_list.append(accuracy)

# 在训练循环后，添加以下代码plt.figure(figsize=(12, 4))# 可视化损失plt.subplot(1, 2, 1)plt.plot(range(1, num_epochs + 1), train_loss_list, label='Training Loss')plt.title('Training Loss')plt.xlabel('Epochs')plt.ylabel('Loss')plt.legend()# 可视化准确率plt.subplot(1, 2, 2)plt.plot(range(1, num_epochs + 1), accuracy_list, label='Accuracy')plt.title('Accuracy')plt.xlabel('Epochs')plt.ylabel('Accuracy')plt.legend()plt.tight_layout()plt.show()