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 votes108 views1 answer
Python short circuit
Python
0 vote147 views1 answer
How to read a pkl file in python
Python
0 vote120 views1 answer
Python toupls
Python
0 vote129 views1 answer
Python ignore first value in generator
Python
1 vote139 views1 answer
Pythin load .csv
Python
1 vote122 views1 answer
Delimiter pandas
Python
0 vote138 views1 answer
Python remove suffix
Python
0 vote131 views1 answer
Change image in tkinter canvas
Python
-1 vote135 views1 answer
Popup window python tkinter
Python
0 vote140 views1 answer
Python how to get current line number
Python