AttributeError: 'Model' object has no attribute 'parameters'

Question

我正在使用修改后的 Resnet18，在 Resnet 的末尾有我自己的池化函数。

这是我的代码：

resnet = resnet18().cuda() #a modified resnet

class Model():
    def __init__(self, model, pool):
        self.model = model
        self.pool= pool #my own pool class which has trainable layers

    def forward(self, sample):
        output = self.model(sample)
        output = self.pool(output)
        output = F.normalize(output, p=2, dim=1)
        return output

现在，显然我不仅需要训练 resnet 部分，还需要训练池部分。

但是，当我检查时：

model = Model(model=resnet, pool= pool)
print(list(model.parameters()))

它给出：

AttributeError: 'Model' object has no attribute 'parameters'

有人能帮忙吗？

Answer 1

您需要 Model 才能继承 torch.nn.Module:

class Model(torch.nn.Module):
    def __init__(self, model, pool):
        super(Model, self).__init__()
        ...

AttributeError: 'Model' object has no attribute 'parameters'

AttributeError: 'Model' object has no attribute 'parameters'

pytorch

resnet