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

14 votes183 views6 answers
Binary search python
Python
0 vote173 views1 answer
Sorting tuples
Python
0 vote202 views1 answer
Set default value in funtion in python hackrank Compress the String!
Python
0 vote198 views1 answer
ValueError: columns overlap but no suffix specified:
Python
0 vote221 views2 answers
How to get current page url in django template
Python Django
0 vote187 views1 answer
Defaultdict python inport
Python
1 vote194 views1 answer
Any python type hint
Python
0 vote197 views1 answer
Find maximum value by if else python
Python
1 vote250 views1 answer
How to get chat first name in telebot
Python
0 vote187 views2 answers
Discord.py send message to channel with mutiple id
Python