Hai,
Can anyone provide me the way of using adaptive regularizer?
say
reg += torch.sum(torch.mul(w,w)-a)
I need the a to be trainable, how should i do that?
Thanks in advance!
Hai,
Can anyone provide me the way of using adaptive regularizer?
say
reg += torch.sum(torch.mul(w,w)-a)
I need the a to be trainable, how should i do that?
Thanks in advance!
If you want a
to be a parameter of the model wrap it around nn.Parameter
. In your nn.Module
add this line: self.a = nn.Parameter(torch.tensor(0.5), requires_grad=True)
, where 0.5 is the initialization value.