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

1 vote271 views1 answer
Minimum-number-of-steps-to-reduce-number-to-1
Python
18 votes246 views4 answers
Bubble sort in python
Python
10 votes247 views1 answer
How to varify pip is install in python
Python
0 vote294 views1 answer
KeyError: 'ProfilePage'
Python
3 votes265 views2 answers
How to check if text is in upper case in python
Python
1 vote259 views1 answer
Directly changing the fonts in the plotting file
Python
0 vote291 views1 answer
Python yyyymmdd
Python
0 vote271 views1 answer
Break up word in clomun pandas
Python
0 vote268 views1 answer
Gensim show_topics get topic
Python
0 vote288 views2 answers
Add key value in each dictonary in the list
Python