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 vote388 views1 answer
Pandas group by concat
Python
1 vote349 views1 answer
Start python virtual
Python
0 vote333 views1 answer
Scipy version check
Python
0 vote330 views1 answer
Returns all column names as a list
Python
6 votes343 views5 answers
Django logout
Python Django
0 vote355 views1 answer
Sikuli guide text
Python
0 vote340 views1 answer
Create image tkinter set active background
Python
210 votes499 views6 answers
Looping over dictionary python
Python
0 vote391 views1 answer
Add favicon in django admin
Python Django
0 vote339 views1 answer
\n vs \r python
Python