pytorch定义神经网络模型的方法

在 PyTorch 中，定义神经网络模型的方法有以下几步：

1. 导入必要的库

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

2. 定义模型类

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        # 定义各种层
        self.conv1 = nn.Conv2d(1, 6, 3)
        self.conv2 = nn.Conv2d(6, 16, 3)
        self.fc1 = nn.Linear(16 * 6 * 6, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # 定义前向传播
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        # 辅助函数，计算特征数量
        size = x.size()[1:]  
        num_features = 1  
        for s in size:
            num_features *= s
        return num_features

3. 实例化模型

net = Net()

4. 定义损失函数和优化器

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

5. 训练模型

for epoch in range(2):  # 多次迭代
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        optimizer.zero_grad()  # 清除梯度缓存
        outputs = net(inputs)  # 正向传播
        loss = criterion(outputs, labels)  # 计算损失
        loss.backward()  # 反向传播
        optimizer.step()  # 更新参数

        running_loss += loss.item()
        if i % 2000 == 1999:  # 每 2000 次迭代打印一次损失
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

6. 保存模型

PATH = './cifar_net.pth'
torch.save(net.state_dict(), PATH)

以上是 PyTorch 中定义神经网络模型的基本方法，具体实现可以根据实际需求进行更改。