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 vote140 views1 answer
How to print something with tkinter
Python
0 vote138 views1 answer
How to check if given primary key exists in django model
Python
0 vote163 views1 answer
Ignore transformers warning
Python
1 vote126 views1 answer
Python information
Python
0 vote126 views1 answer
Output of an intermediate layer
Python
0 vote191 views1 answer
Count entries groupby
Python
0 vote126 views1 answer
Sang nguyen to python
Python
0 vote147 views1 answer
Fillna with index
Python
-1 vote96 views1 answer
Ten minute mail
Python
1 vote133 views1 answer
Create zero array in python
Python