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

2 votes372 views3 answers
Play mp3 file python
Python
22 votes329 views4 answers
No module named 'sklearn.cross_validation'
Python
31 votes303 views5 answers
Image in tkinter
Python
-1 vote334 views2 answers
Python dict remove duplicates where name are not the same
Python
43 votes393 views6 answers
Reverse string python
Python
0 vote322 views1 answer
Django sign up
Python
16 votes295 views2 answers
Install django using pip
Python
0 vote326 views1 answer
Mnist
Python
68 votes305 views6 answers
Python create directory
Python
1 vote308 views1 answer
Python retry
Python