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 vote243 views1 answer
Save pythonpath
Python
0 vote240 views2 answers
Python int string float
Python
0 vote230 views1 answer
Java sript
Python
12 votes233 views1 answer
Copy a dict in python
Python
16 votes221 views6 answers
Print() in python
Python
0 vote227 views2 answers
Code.org void loops
Python
0 vote224 views1 answer
Code folding vim python
Python
0 vote255 views2 answers
Create dictionary without removing duplicates from dataframe
Python
1 vote218 views3 answers
Program to draw rectangle in python
Python
3 votes212 views3 answers
Pandas change multiple column types
Python