【零基础入门】CIFAR-10图像分类实战：从数据到模型，小白也能轻松上手！

pip install torch torchvision matplotlib transform

import torch
import torchvision
import torchvision.transforms as transforms

# 数据转换和归一化
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

# 加载数据集
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)

testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False)

import torch.nn as nn
import torch.nn.functional as F

class SimpleCNN(nn.Module):
    def __init__(self):
        super(SimpleCNN, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, 3, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(32, 64, 3, padding=1)
        self.fc1 = nn.Linear(64 * 8 * 8, 64)
        self.fc2 = nn.Linear(64, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 64 * 8 * 8)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

model = SimpleCNN()

import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
for epoch in range(10):  # 训练10个epoch
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if i % 100 == 99:  # 每100个批次打印一次损失
            print(f'Epoch {epoch + 1}, Batch {i + 1}, Loss: {running_loss / 100:.3f}')
            running_loss = 0.0

print('Finished Training')

correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print(f'Accuracy of the network on the 10000 test images: {100 * correct / total:.2f}%')

# 可视化损失值
plt.figure(figsize=(10, 5))
plt.plot(loss_values, label='Training Loss')
plt.xlabel('Batch (x100)')
plt.ylabel('Loss')
plt.title('Training Loss Over Time')
plt.legend()
plt.savefig('training_loss.png')  # Save the loss plot
plt.show()

def imshow(img, filename=None):
    plt.figure()  # 为图像创建一个新的图形
    img = img / 2 + 0.5  # 反归一化
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    if filename:
        plt.savefig(filename)  # 保存图像
    plt.show()

# 获取一些随机测试图像
dataiter = iter(testloader)
images, labels = next(dataiter)
imshow(torchvision.utils.make_grid(images), 'test_images.png')
outputs = model(images)
_, predicted = torch.max(outputs, 1)

print('Predicted: ', ' '.join(f'{trainset.classes[predicted[j]]}' for j in range(4)))

torch.save(model.state_dict(), 'cifar10_model.pth')