How to fix model's parameter

I’m learning doubleDQN, now I want to calculate a Variable by using a model, and then backward a loss calculated from the Variable, but I do not want to optimize the model’s parameters, How to do that?

you just want to run one iteration?

Two different solutions you can try.

  1. You can specify to not process the gradient on a Variable with : variable.requires_grad = False
    Then use your optimizer as:
optimizer = torch.optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), learning_rate)
  1. Process the gradient on all your Variables and choose which one you want to update with your optimizer.
                {'params': model.base.parameters()},
                {'params': model.classifier.parameters(), 'lr': 1e-3}
            ], lr=1e-2, momentum=0.9)

Hi Cadene,
May I know what is the lambda p: p here and how does it work? Shouldn’t it be lambda variable: variable.requires_grad?