pytorch全连接神经网络来对 MNIST 数据集进行分类

步骤概览

1. 安装依赖
2. 导入必要的库
3. 定义模型
4. 加载数据
5. 定义损失函数和优化器
6. 训练模型
7. 测试模型

1. 安装依赖

确保你已经安装了 PyTorch 和 torchvision。如果还没有安装，可以使用以下命令：

conda install pytorch torchvision torchaudio cpuonly -c pytorch

或者使用 pip：

pip install torch torchvision

2. 导入必要的库

import torch import torch.nn as nn 
import torch.optim as optim 
import torchvision 
import torchvision.transforms as transforms

3. 定义模型

定义一个简单的全连接神经网络：

class SimpleNN(nn.Module):
    def __init__(self):
        super(SimpleNN, self).__init__()
        self.fc1 = nn.Linear(28*28, 512)
        self.fc2 = nn.Linear(512, 256)
        self.fc3 = nn.Linear(256, 10)
    
    def forward(self, x):
        x = x.view(-1, 28*28)  # Flatten the input
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

model = SimpleNN()

4. 加载数据

使用 torchvision 来加载和预处理 MNIST 数据集：

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])

trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=32, shuffle=True)

testset = torchvision.datasets.MNIST(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=32, shuffle=False)

5. 定义损失函数和优化器

使用交叉熵损失函数和 Adam 优化器：

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

6. 训练模型

定义训练过程：

num_epochs = 5

for epoch in range(num_epochs):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        
        # Zero the parameter gradients
        optimizer.zero_grad()
        
        # Forward + backward + optimize
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
        # Print statistics
        running_loss += loss.item()
        if i % 200 == 199:  # Print every 200 mini-batches
            print(f'Epoch [{epoch + 1}/{num_epochs}], Step [{i + 1}/{len(trainloader)}], Loss: {running_loss / 200:.4f}')
            running_loss = 0.0

print('Finished Training')

7. 测试模型

定义测试过程并计算模型在测试集上的准确性：

num_epochs = 5

for epoch in range(num_epochs):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        
        # Zero the parameter gradients
        optimizer.zero_grad()
        
        # Forward + backward + optimize
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
        # Print statistics
        running_loss += loss.item()
        if i % 200 == 199:  # Print every 200 mini-batches
            print(f'Epoch [{epoch + 1}/{num_epochs}], Step [{i + 1}/{len(trainloader)}], Loss: {running_loss / 200:.4f}')
            running_loss = 0.0

print('Finished Training')

完整代码

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms

# 定义模型
class SimpleNN(nn.Module):
    def __init__(self):
        super(SimpleNN, self).__init__()
        self.fc1 = nn.Linear(28*28, 512)
        self.fc2 = nn.Linear(512, 256)
        self.fc3 = nn.Linear(256, 10)
    
    def forward(self, x):
        x = x.view(-1, 28*28)  # Flatten the input
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

model = SimpleNN()

# 加载数据
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])

trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=32, shuffle=True)

testset = torchvision.datasets.MNIST(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=32, shuffle=False)

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

# 训练模型
num_epochs = 5

for epoch in range(num_epochs):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        
        # 清零参数梯度
        optimizer.zero_grad()
        
        # 前向传播 + 反向传播 + 优化
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
        # 打印统计信息
        running_loss += loss.item()
        if i % 200 == 199:  # 每200个mini-batch打印一次
            print(f'Epoch [{epoch + 1}/{num_epochs}], Step [{i + 1}/{len(trainloader)}], Loss: {running_loss / 200:.4f}')
            running_loss = 0.0

print('Finished Training')

# 测试模型
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}%')