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

Question

I am using a modified Resnet18, with my own pooling function at the end of the Resnet.

Here is my code:

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

Now, obviously I need to train not only the resnet part, but also the pool part.

But, when I check:

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

It gives:

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

Can anyone help?

KonstantinosKokos · Accepted Answer · 2021-05-26 14:27:58Z

3

You need you Model to inherit torch.nn.Module:

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

answered May 26, 2021 at 14:27

KonstantinosKokos

3,4831 gold badge13 silver badges23 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Khabbab Zakaria Over a year ago

Oh yes! right! Can you tell me how to print the parameters separately for the resnet and pool?

KonstantinosKokos Over a year ago

pool and resnet are themselves modules, so you can simply print(model.pool.parameters()) (ditto for resnet)

Collectives™ on Stack Overflow

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

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related