Pytorch l2 regularization

# add l2 regularization to optimzer by just adding in a weight_decay 
optimizer = torch.optim.Adam(model.parameters(),lr=1e-4,weight_decay=1e-5)

Regularization pytorch

 loss = mse(pred, target)
 l1 = 0
 for p in net.parameters():
  l1 = l1 + p.abs().sum()
 loss = loss + lambda_l1 * l1
 loss.backward()
 optimizer.step()

Source: discuss.pytorch.org

Similar codes

0 vote137 views1 answer
Python wait for executable to finish before perceeding
Python
0 vote139 views1 answer
Highlight Active Links in Django Website
Python Django
0 vote114 views1 answer
Replace string if it contains a substring pandas
Python
3 votes100 views1 answer
Python nested functions get variables from function scope
Python
0 vote98 views1 answer
Pandas Timedelta to postgres
Python
1 vote108 views1 answer
Np.rand.randint
Python
0 vote100 views2 answers
Conda install dash
Python
0 vote140 views1 answer
TypeError: Direct assignment to the forward side of a many-to-many set is prohibited. Use .set() instead
Python
0 vote106 views1 answer
How change column strin of list data type to list
Python
0 vote110 views1 answer
Docstrinfs pyt
Python