时间戳

首页 > 解决方案 > 可以结合2个神经网络吗？

deep-learning - 可以结合2个神经网络吗？

问题描述

我有一个 NET （示例来自这里）

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120)  # 5*5 from image dimension
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square, you can specify with a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = torch.flatten(x, 1) # flatten all dimensions except the batch dimension
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
net = Net()

和另一个网络（例如here）

class binaryClassification(nn.Module):
    def __init__(self):
        super(binaryClassification, self).__init__()
        # Number of input features is 12.
        self.layer_1 = nn.Linear(12, 64) 
        self.layer_2 = nn.Linear(64, 64)
        self.layer_out = nn.Linear(64, 1) 
        self.relu = nn.ReLU()
        self.dropout = nn.Dropout(p=0.1)
        self.batchnorm1 = nn.BatchNorm1d(64)
        self.batchnorm2 = nn.BatchNorm1d(64)
        
    def forward(self, inputs):
        x = self.relu(self.layer_1(inputs))
        x = self.batchnorm1(x)
        x = self.relu(self.layer_2(x))
        x = self.batchnorm2(x)
        x = self.dropout(x)
        x = self.layer_out(x)
        return x

我想更改，例如“self.fc2 = nn.Linear(120, 84)”以便有 121 个输入，其中第 121 个是 binaryClassification 网络的 x（输出）。想法是：我想同时使用 CNN 网络和非 CNN 网络来训练两者，相互影响。

可能吗？我该怎么做？（Keras 或 Pytorch 示例都可以）。

或者这个想法很疯狂，并且有更简单的方法可以将数据和图像混合为独特网络的输入？

标签： deep-learningneural-networkpytorchconv-neural-network

解决方案

最简单的方法是实例化两个模型，将两个预测相加并用它计算损失。这将通过两个模型进行反向传播：

net1 = Net1()
net2 = Net2()
bce = torch.nn.BCEWithLogitsLoss()
params = list(net1.parameters()) + list(net2.parameters())
optimizer = optim.SGD(params)
for (x, ground_truth) in enumerate(your_data_loader):
    optimizer.zero_grad()
    prediction = net1(x) + net2(x)  # the 2 models must output tensors of same shape
    loss = bce(prediction, ground_truth)
    train_loss.backward()
    optimizer.step()

你也可以例如

  • 在单个模型中实现 Net1 和 Net2 的层
  • 分别训练 Net1 和 Net2 并在以后集成它们

推荐阅读