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 vote213 views1 answer
Does python have a end of line symbol
Python
2 votes194 views1 answer
Removing punctuation with NLTK in Python
Python
0 vote193 views1 answer
How to get function help in jupyter notebook
Python
6 votes304 views4 answers
Install python3 in ubuntu
Python
0 vote193 views1 answer
Multivariable traces f(x, y) = sin(x)cos(y)
Python
1 vote197 views1 answer
Show number as 3 digit python
Python
1 vote188 views1 answer
Python your mom
Python
2 votes189 views4 answers
ValueError: Input contains NaN, infinity or a value too large for dtype('float32').
Python
0 vote245 views1 answer
Python append variable to list
Python
0 vote235 views1 answer
How to save model to a file python
Python