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

41 votes361 views5 answers
.replace python
Python
4 votes332 views1 answer
Numpy mean 2 arrays
Python
3 votes359 views1 answer
Isaplha in python
Python
3 votes344 views2 answers
Encryption using python
Python
1 vote496 views2 answers
Django password hashing
Python Django
1 vote443 views1 answer
Pygame mute import message
Python
0 vote409 views1 answer
Series object has no attribute columns
Python
61 votes330 views6 answers
Python get dir
Python
1 vote354 views1 answer
Plt line of best fit
Python
0 vote316 views1 answer
Axes turn of axis matplotlb
Python