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

6 votes254 views1 answer
Python regex replace all non alphanumeric characters
Python
0 vote257 views1 answer
Argparse one argument or without argument
Python
5 votes238 views2 answers
Tables in jinja template
Python
0 vote265 views1 answer
Excel write in row
Python
0 vote250 views1 answer
Mute button tkinter
Python
1 vote238 views1 answer
Python remove multiple characters from string
Python
1 vote223 views1 answer
Python get newest file in directory
Python
0 vote223 views1 answer
Change state of tkintr btn
Python
2 votes234 views2 answers
Update python in miniconda
Python
-1 vote244 views1 answer
How to find root value python
Python