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 vote148 views1 answer
Color plt
Python
25 votes164 views4 answers
Python pil
Python
5 votes140 views1 answer
Python plot multiple lines in same figure
Python
1 vote164 views1 answer
Postgres django settings
Python
8 votes160 views4 answers
Zip a directory in python
Python
-2 votes154 views1 answer
Python for-while
Python
3 votes149 views2 answers
Scapy python import
Python
1 vote149 views1 answer
Rum system commands python
Python
0 vote142 views1 answer
Remove dot from number python
Python
3 votes155 views2 answers
Correlation analysis of dataframe python
Python