PyTorch 实现 MNIST 手写数字识别

MNIST 是一个经典的手写数字数据集，包含 60000 张训练图像和 10000 张测试图像。使用 PyTorch 实现 MNIST 分类通常包括数据加载、模型构建、训练和评估几个部分。

数据加载与预处理

使用 torchvision 加载 MNIST 数据集，并进行归一化和数据增强（可选）。以下是数据加载的示例代码：

复制代码

import torch
from torchvision import datasets, transforms

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

train_dataset = datasets.MNIST('data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST('data', train=False, transform=transform)

train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=1000, shuffle=False)

构建模型

定义一个简单的卷积神经网络（CNN）模型：

复制代码

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

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.fc1 = nn.Linear(1024, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.max_pool2d(x, 2)
        x = F.relu(self.conv2(x))
        x = F.max_pool2d(x, 2)
        x = torch.flatten(x, 1)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

训练模型

定义优化器和损失函数，并进行训练：

复制代码

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

def train(model, device, train_loader, optimizer, 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(f'Epoch: {epoch}, Loss: {loss.item():.4f}')

测试模型

在测试集上评估模型性能：

复制代码

def test(model, device, test_loader):
    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()
            pred = output.argmax(dim=1, keepdim=True)
            correct += pred.eq(target.view_as(pred)).sum().item()
    test_loss /= len(test_loader.dataset)
    print(f'Test Accuracy: {correct}/{len(test_loader.dataset)} ({100. * correct / len(test_loader.dataset):.2f}%)')

完整训练循环

将训练和测试整合到一个完整的循环中：进行10次训练

复制代码

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

for epoch in range(1, 10):
    train(model, device, train_loader, optimizer, epoch)
    test(model, device, test_loader)

模型保存与加载

训练完成后，可以保存模型：

复制代码

torch.save(model.state_dict(), 'mnist_cnn.pt')

加载模型：

加载模块

复制代码

model = Net()
model.load_state_dict(torch.load('mnist_cnn.pt'))
model.eval()

或者是Mnist其他源代码

Mnist main.py

python 复制代码

import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.optim.lr_scheduler import StepLR


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.dropout1 = nn.Dropout(0.25)
        self.dropout2 = nn.Dropout(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output

#训练模型
def train(args, model, device, train_loader, optimizer, 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 = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 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()))
            if args.dry_run:
                break

#测试模型
def test(model, device, test_loader):
    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 += F.nll_loss(output, target, reduction='sum').item()  # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True)  # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)

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

#主函数 MNIST Example的主函数
def main():
    # Training settings
    parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
    parser.add_argument('--batch-size', type=int, default=64, metavar='N',
                        help='input batch size for training (default: 64)')
    parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
                        help='input batch size for testing (default: 1000)')
    parser.add_argument('--epochs', type=int, default=14, metavar='N',
                        help='number of epochs to train (default: 14)')
    parser.add_argument('--lr', type=float, default=1.0, metavar='LR',
                        help='learning rate (default: 1.0)')
    parser.add_argument('--gamma', type=float, default=0.7, metavar='M',
                        help='Learning rate step gamma (default: 0.7)')
    parser.add_argument('--no-accel', action='store_true',
                        help='disables accelerator')
    parser.add_argument('--dry-run', action='store_true',
                        help='quickly check a single pass')
    parser.add_argument('--seed', type=int, default=1, metavar='S',
                        help='random seed (default: 1)')
    parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                        help='how many batches to wait before logging training status')
    parser.add_argument('--save-model', action='store_true', 
                        help='For Saving the current Model')
    args = parser.parse_args()

    use_accel = not args.no_accel and torch.accelerator.is_available()

    torch.manual_seed(args.seed)

    if use_accel:
        device = torch.accelerator.current_accelerator()
    else:
        device = torch.device("cpu")

    train_kwargs = {'batch_size': args.batch_size}
    test_kwargs = {'batch_size': args.test_batch_size}
    if use_accel:
        accel_kwargs = {'num_workers': 1,
                       'pin_memory': True,
                       'shuffle': True}
        train_kwargs.update(accel_kwargs)
        test_kwargs.update(accel_kwargs)

    transform=transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
        ])
    dataset1 = datasets.MNIST('../data', train=True, download=True,
                       transform=transform)
    dataset2 = datasets.MNIST('../data', train=False,
                       transform=transform)
    train_loader = torch.utils.data.DataLoader(dataset1,**train_kwargs)
    test_loader = torch.utils.data.DataLoader(dataset2, **test_kwargs)

    model = Net().to(device)
    optimizer = optim.Adadelta(model.parameters(), lr=args.lr)

    scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma)
    for epoch in range(1, args.epochs + 1):
        train(args, model, device, train_loader, optimizer, epoch)
        test(model, device, test_loader)
        scheduler.step()

    if args.save_model:
        torch.save(model.state_dict(), "mnist_cnn.pt")


if __name__ == '__main__':
    main()

带命令的Mnist函数

python 复制代码

python main.py --help
usage: main.py [-h] [--batch-size N] [--test-batch-size N] [--epochs N] [--lr LR] [--gamma M] [--no-accel]
               [--dry-run] [--seed S] [--log-interval N] [--save-model]

PyTorch MNIST Example

optional arguments:
  -h, --help           show this help message and exit
  --batch-size N       input batch size for training (default: 64)
  --test-batch-size N  input batch size for testing (default: 1000)
  --epochs N           number of epochs to train (default: 14)
  --lr LR              learning rate (default: 1.0)
  --gamma M            Learning rate step gamma (default: 0.7)
  --no-accel           disables accelerator
  --dry-run            quickly check a single pass
  --seed S             random seed (default: 1)
  --log-interval N     how many batches to wait before logging training status
  --save-model         For Saving the current Model

数据目录

注意事项

确保安装了 PyTorch 和 torchvision 库。
可以根据硬件条件调整 batch_size。
模型结构和超参数（如学习率）可以根据需求调整。
使用 GPU 可以显著加速训练。