x = self.layer1(x) x = self.layer2(x) x = x.view(-1, 64*7*7)写出forward里加入dropout层的变化

可以在每个层的输出之后加上一个dropout层，在训练过程中随机失活一部分神经元，以减少过拟合的风险。修改后的代码如下：

import torch.nn as nn

class MyNet(nn.Module):
    def __init__(self):
        super(MyNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(in_channels=3, out_channels=32, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.dropout1 = nn.Dropout(p=0.2)  # 加入dropout层
        self.layer2 = nn.Sequential(
            nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.dropout2 = nn.Dropout(p=0.2)  # 加入dropout层
        self.fc = nn.Sequential(
            nn.Linear(in_features=64*7*7, out_features=1024),
            nn.ReLU(),
            nn.Linear(in_features=1024, out_features=10))

    def forward(self, x):
        x = self.layer1(x)
        x = self.dropout1(x)  # 加入dropout层
        x = self.layer2(x)
        x = self.dropout2(x)  # 加入dropout层
        x = x.view(-1, 64*7*7)
        x = self.fc(x)
        return x

在实际使用中，我们可以根据数据集和模型的表现调整dropout层的概率，以达到更好的效果。