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

4 votes138 views1 answer
How to calculate rmse in linear regression python
Python
3 votes155 views2 answers
Python get current mouse position
Python
1 vote117 views1 answer
How to find magnitude of complex number in python
Python
1 vote116 views2 answers
Set jupyer color to dark
Python
0 vote143 views6 answers
Idl else
Python
0 vote137 views1 answer
Non venomous snakes
Python
3 votes158 views2 answers
Python save a dictionary as an object
Python
0 vote120 views1 answer
Pygame get surface region
Python
19 votes133 views5 answers
Run python file from another python file
Python
0 vote123 views1 answer
How to increase size of graph in jupyter
Python