创建一个模型，其权重是 2 个不同神经网络的权重之和

Question

我正在做迁移学习的实验。我训练了 2 个具有完全相同结构的 CNN，一个用于 MNIST，一个用于 SVHN。我获得了 2 个模型的参数（权重和偏差）。现在，我想合并（求和或其他操作）这些权重。像这样的事情：

modelMNIST.parameters()
modelSVHN.parameters()

#now the new model
model3 = MyCNN(1)
model3.parameters = modelMNIST.parameters()+modelSVHN.parameters()

如果我这样做，我会得到这个错误： SyntaxError: can't assign to function call

然后这样：

model3.block_1[0].weight = modelMNIST.block_1[0].weight + modelSVHN.block_1[0].weight

我收到这个错误：

TypeError: cannot assign 'torch.cuda.FloatTensor' as parameter 'weight' (torch.nn.Parameter or None expected)

有什么方法可以合并不同模型的权重吗？

Answer 1

您需要更新参数的 .data 属性。 Parameter 不是 FloatTensor，因此是错误。

由于两个网络相同，您可以使用以下代码更新权重。

for param1, param2 in zip(modelMNIST.parameters(), modelSVHN.parameters()):
     param1.data += param2.data

Answer 2

我的解决方案是这样的：

class VGG16SUM(nn.Module):
    
    def __init__(self, model1, model2, num_classes):
        super(VGG16SUM, self).__init__()

        # calculate same padding:
        # (w - k + 2*p)/s + 1 = o
        # => p = (s(o-1) - w + k)/2

        self.block_1 = nn.Sequential(
            nn.Conv2d(in_channels=1,
                      out_channels=64,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      # (1(32-1)- 32 + 3)/2 = 1
                      padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.Conv2d(in_channels=64,
                      out_channels=64,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2),
                         stride=(2, 2))
        )

        self.block_2 = nn.Sequential(
            nn.Conv2d(in_channels=64,
                      out_channels=128,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU(),
            nn.Conv2d(in_channels=128,
                      out_channels=128,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2),
                         stride=(2, 2))
        )
        
        self.block_3 = nn.Sequential(
            nn.Conv2d(in_channels=128,
                      out_channels=256,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.Conv2d(in_channels=256,
                      out_channels=256,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.Conv2d(in_channels=256,
                      out_channels=256,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2),
                         stride=(2, 2))
        )

        self.block_4 = nn.Sequential(
            nn.Conv2d(in_channels=256,
                      out_channels=512,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.Conv2d(in_channels=512,
                      out_channels=512,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.Conv2d(in_channels=512,
                      out_channels=512,
                      kernel_size=(3, 3),
                      stride=(1, 1),
                      padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2),
                         stride=(2, 2))
        ) 


        self.classifier = nn.Sequential(
            nn.Linear(2048, 4096),
            nn.ReLU(True),
            nn.Dropout(p=0.25),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(p=0.25),
            nn.Linear(4096, num_classes),
        )

        for p_out, p_in1, p_in2 in zip(self.parameters(), model1.parameters(), model2.parameters()):
            p_out.data = nn.Parameter(p_in1 +p_in2);

    def forward(self, x):

        x = self.block_1(x)
        x = self.block_2(x)
        x = self.block_3(x)
        x = self.block_4(x)
        # x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.classifier(x)
        return x
        #logits = self.classifier(x)
        #probas = F.softmax(logits, dim=1)
        # probas = nn.Softmax(logits)
        #return probas
        # return logits

有效！！！

创建一个模型，其权重是 2 个不同神经网络的权重之和

Creating a model which weights are the sum of weights of 2 different neural networks

neural-network

mnist

conv-neural-network

pytorch

transfer-learning