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 vote197 views1 answer
Sort files in windows order python
Python
0 vote222 views1 answer
Complex arrays python
Python
0 vote207 views1 answer
Inject dynamic value into string python
Python
0 vote230 views2 answers
Pandas select rows by condition in list
Python
1 vote217 views2 answers
Datetime to epoch
Python
7 votes216 views2 answers
Pygame rotate image
Python
0 vote260 views1 answer
Django action when create model
Python Django
30 votes218 views3 answers
Python max key dictionary key getter
Python
1 vote192 views1 answer
Get the system boot time in python
Python
6 votes187 views4 answers
Python commenting
Python