import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms# 定义神经网络结构
class SimpleNN(nn.Module):def __init__(self, input_size, hidden_size, num_classes):super(SimpleNN, self).__init__()self.fc1 = nn.Linear(input_size, hidden_size)self.relu = nn.ReLU()self.fc2 = nn.Linear(hidden_size, num_classes)def forward(self, x):out = self.fc1(x)out = self.relu(out)out = self.fc2(out)return out# 设置超参数
input_size = 784 # MNIST数据集的输入大小是28x28=784
hidden_size = 784
num_classes = 10learning_rate = 0.01
num_epochs = 10# 加载MNIST数据集
train_dataset = torchvision.datasets.MNIST(root='./data', train=True, transform=transforms.ToTensor(), download=True)
test_dataset = torchvision.datasets.MNIST(root='./data', train=False, transform=transforms.ToTensor())# 数据加载器
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=100, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=100, shuffle=False)# 实例化模型
model = SimpleNN(input_size, hidden_size, num_classes)# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)# 训练模型
total_step = len(train_loader)
for epoch in range(num_epochs):for i, (images, labels) in enumerate(train_loader):# 将输入数据转换为一维向量images = images.reshape(-1, 28*28)# 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()if (i+1) % 100 == 0:print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, i+1, total_step, loss.item()))# 测试模型
with torch.no_grad():correct = 0total = 0for images, labels in test_loader:images = images.reshape(-1, 28*28)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))# 获取模型参数
params = model.parameters()# 打印每个参数的名称和值
for name, param in model.named_parameters():print(f'Parameter name: {name}')print(f'Parameter value: {param}')以下代码测试正确率为：99.37%
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms# 定义适合MNIST数据集的CNN模型
class MNISTCNN(nn.Module):def __init__(self):super(MNISTCNN, self).__init__()# 卷积块 1self.conv_block1 = nn.Sequential(nn.Conv2d(in_channels=1, out_channels=32, kernel_size=3, padding=1),nn.ReLU(),nn.MaxPool2d(kernel_size=2))# 卷积块 2self.conv_block2 = nn.Sequential(nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, padding=1),nn.ReLU(),nn.MaxPool2d(kernel_size=2))# 全连接层self.fc_layer = nn.Sequential(nn.Linear(64 * 7 * 7, 512), # 假设经过前面的卷积和池化后特征图大小为7x7nn.ReLU(),nn.Dropout(p=0.5),nn.Linear(512, 10) # MNIST有10个类别)def forward(self, x):x = self.conv_block1(x)x = self.conv_block2(x)# 将卷积层输出展平为一维向量x = x.view(x.size(0), -1)# 通过全连接层x = self.fc_layer(x)return x# 创建模型实例
model = MNISTCNN()# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)# 加载MNIST数据集并预处理
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST(root='./data', train=False, download=True, transform=transform)# 使用DataLoader加载批量数据
batch_size = 64
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=False)# 开始训练
num_epochs = 10
for epoch in range(num_epochs):for inputs, labels in train_loader:# 前向传播outputs = model(inputs)loss = criterion(outputs, labels)# 反向传播和优化optimizer.zero_grad() # 清空梯度缓存loss.backward() # 计算梯度optimizer.step() # 更新参数# 每个epoch结束时打印损失print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')# 测试模型
model.eval() # 将模型切换到评估模式（禁用Dropout和BatchNorm等）
with torch.no_grad():correct = 0total = 0for images, labels in test_loader:outputs = model(images)_, predicted = torch.max(outputs.data, 1)total += labels.size(0)correct += (predicted == labels).sum().item()print(f'Test Accuracy: {100 * correct / total}%')
)
