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 vote145 views1 answer
KeyError: "'__name__' not in globals" django
Python Django
1 vote106 views1 answer
Python install pandas for linux
Python
0 vote119 views1 answer
Location of matploitlibrc file
Python
30 votes123 views5 answers
Python iterate through files in directory
Python
0 vote120 views1 answer
How to slice few rows in pandas
Python
6 votes108 views2 answers
Python how to drop columns from dataframe
Python
7 votes131 views3 answers
Update django
Python Django
0 vote117 views1 answer
Set value through serializer django
Python
0 vote103 views1 answer
Spansk dansk
Python
0 vote117 views1 answer
Python dictionary get keys with condition on value
Python