minist手写数字识别

MNIST是一个常用的手写数字识别数据集，其中包含了60,000张训练图片和10,000张测试图片。每张图片大小为28x28像素，灰度图像，数字的大小和位置不一定相同。以下是使用Python和PyTorch实现MNIST手写数字识别的基本步骤：

1. 加载MNIST数据集

import torch
import torchvision.datasets as dsets
import torchvision.transforms as transforms

# 定义数据预处理方式
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize(mean=[0.5], std=[0.5])])

# 加载训练集和测试集
train_dataset = dsets.MNIST(root='./data', train=True, transform=transform, download=True)
test_dataset = dsets.MNIST(root='./data', train=False, transform=transform, download=True)

# 定义数据加载器
batch_size = 128
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)

2. 定义模型结构

import torch.nn as nn

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=1, out_channels=32, kernel_size=5, padding=2)
        self.pool1 = nn.MaxPool2d(kernel_size=2)
        self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2)
        self.pool2 = nn.MaxPool2d(kernel_size=2)
        self.fc1 = nn.Linear(in_features=64*7*7, out_features=1024)
        self.fc2 = nn.Linear(in_features=1024, out_features=10)
        self.relu = nn.ReLU()
        self.dropout = nn.Dropout(p=0.5)
        
    def forward(self, x):
        x = self.conv1(x)
        x = self.relu(x)
        x = self.pool1(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = self.pool2(x)
        x = x.view(x.size(0), -1)
        x = self.fc1(x)
        x = self.relu(x)
        x = self.dropout(x)
        x = self.fc2(x)
        return x

3. 定义损失函数和优化器

import torch.optim as optim

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

4. 训练模型

num_epochs = 10

for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        # 前向传播
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # 反向传播和优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        # 每100个batch打印一次训练信息
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Batch [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, len(train_loader), loss.item()))

5. 测试模型

# 测试模型
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

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

完整代码示例请参考：https://github.com/pytorch/examples/blob/master/mnist/main.py