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 vote311 views1 answer
Can a function output be save as a variable python
Python
0 vote263 views1 answer
Fetch json array from mysql django
Python Django
0 vote277 views1 answer
Create jwt token python
Python
0 vote243 views1 answer
Return dataframe as csv flask
Python
0 vote250 views1 answer
Oauthlib python error
Python
3 votes213 views1 answer
Python list insert at front
Python
1 vote277 views1 answer
Animate time series python
Python
1 vote251 views1 answer
Sort and remove duplicates list python
Python
1 vote278 views1 answer
How to get continuous mouse position with pyautogui in python
Python
47 votes291 views5 answers
Sort the dictionary in python
Python