PyTorch训练MNIST数据集的完整示例代码

 不说废话，代码如下（其中加载mnist数据集中root使用你要下载到的地址）

 

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader

# 数据预处理
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])

# 加载MNIST数据集
train_dataset = datasets.MNIST(root=r'D:\pytorch_study\minist_dataset', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST(root=r'D:\pytorch_study\minist_dataset', train=False, download=True, transform=transform)

# 数据加载器
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=1000, shuffle=False)

# 定义模型架构
class MNISTModel(nn.Module):
    def __init__(self):
        super(MNISTModel, self).__init__()
        self.fc1 = nn.Linear(28 * 28, 512)
        self.fc2 = nn.Linear(512, 256)
        self.fc3 = nn.Linear(256, 10)
        self.relu = nn.ReLU()

    def forward(self, x):
        x = x.view(-1, 28 * 28)
        x = self.relu(self.fc1(x))
        x = self.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    # 初始化模型


model = MNISTModel()

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)


# 训练函数
def train(model, device, train_loader, optimizer, criterion, epoch):
    model.train()
    for 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()
        if batch_idx % 100 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                       100. * batch_idx / len(train_loader), loss.item()))

        # 测试函数


def ceshi(model, device, test_loader, criterion):
    model.eval()
    test_loss = 0
    correct = 0
    with 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()  # 将损失累加
            pred = output.argmax(dim=1, keepdim=True)  # 得到预测结果
            correct += pred.eq(target.view_as(pred)).sum().item()  # 计算正确预测的数量

    test_loss /= len(test_loader.dataset)  # 计算平均损失
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))


# 设置设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = model.to(device)

# 训练模型
epochs = 10
for epoch in range(1, epochs + 1):
    train(model, device, train_loader, optimizer, criterion, epoch)
    ceshi(model, device, test_loader, criterion)