优化器获得一个空的参数列表(skorch)

Question

所以，我习惯了使用PyTorch，现在决定给Skorch一次机会。

Here他们将网络定义为

class ClassifierModule(nn.Module):
    def __init__(
            self,
            num_units=10,
            nonlin=F.relu,
            dropout=0.5,
    ):
        super(ClassifierModule, self).__init__()
        self.num_units = num_units
        self.nonlin = nonlin
        self.dropout = dropout

        self.dense0 = nn.Linear(20, num_units)
        self.nonlin = nonlin
        self.dropout = nn.Dropout(dropout)
        self.dense1 = nn.Linear(num_units, 10)
        self.output = nn.Linear(10, 2)

    def forward(self, X, **kwargs):
        X = self.nonlin(self.dense0(X))
        X = self.dropout(X)
        X = F.relu(self.dense1(X))
        X = F.softmax(self.output(X), dim=-1)
        return X

我更喜欢在每一层中输入神经元列表，即num_units=[30,15,5,2]将有两个隐藏层，分别有15个和5个神经元。此外，我们有30个特性和2个类，因此将其重写为如下所示

class Net(nn.Module):
    def __init__(
            self,
            num_units=[30,15,5,2],
            nonlin=[F.relu,F.relu,F.relu],
            dropout=[0.5,0.5,0.5],
            ):
        super(Net, self).__init__()

        self.layer_units = layer_units     
        self.nonlin = nonlin #Activation function
        self.dropout = dropout #Drop-out rates in each layer
        self.layers = [nn.Linear(i,p) for i,p in zip(layer_units,layer_units[1:])] #Dense layers



    def forward(self, X, **kwargs):
        print("Forwards")
        for layer,func,drop in zip(self.layers[:-1],self.nonlin,self.dropout):
            print(layer,func,drop)
            X=drop(func(layer(X)))


        X = F.softmax(X, dim=-1)
        return X

应该能行得通。问题是当调用

net = NeuralNetClassifier(Net,max_epochs=20,lr=0.1,device="cuda")
net.fit(X,y)

我得到错误"ValueError:优化器得到一个空的参数列表“。我已经将范围缩小到删除self.output = nn.Linear(10, 2)只是使网络不进入forward，即看起来output是某种“触发器”变量。网络最终需要一个名为output (作为一个层)的变量，而我们不能自由定义变量名，这是真的吗？

Answer 1

Pytorch将查找nn.Module的子类，因此更改

self.layers = [nn.Linear(i,p) for i,p in zip(layer_units,layer_units[1:])]

至

self.layers = nn.ModuleList([nn.Linear(i,p) for i,p in zip(layer_units,layer_units[1:])])

应该可以正常工作