通过nn.Parameter实现自适应参数学习的并行CNN

class CNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(
            in_channels=1, out_channels=64, kernel_size=3, stride=1, padding=1
        )
        self.relu1 = nn.ReLU()
        self.conv2 = nn.Conv2d(
            in_channels=64, out_channels=3, kernel_size=3, stride=1, padding=1
        )
        self.relu2 = nn.ReLU()
        self.mlp = nn.Sequential(
            nn.Flatten(),
            nn.Linear(3 * 28 * 28, 512),
            nn.ReLU(),
            nn.Linear(512, 10),
        )

    def forward(self, x):
        x = self.relu1(self.conv1(x))
        x = self.relu2(self.conv2(x))
        return self.mlp(x)

# 定义模型

class MultiCNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.cnn1 = CNN()
        self.cnn2 = CNN()
        self.weight = nn.Parameter(torch.randn(2))

    def forward(self, x):
        x1 = self.cnn1(x)
        x2 = self.cnn2(x)
        y = x1 * self.weight[0] + x2 * self.weight[1]
        return y

# 其他超参数
epochs = 10
batch_size = 64
learning_rate = 1e-3
model = MultiCNN().to(device)
train_loader = DataLoader(train_data, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_data, batch_size=batch_size, shuffle=True)
loss_fn = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)