Pytorch l2 regularization

# add l2 regularization to optimzer by just adding in a weight_decay 
optimizer = torch.optim.Adam(model.parameters(),lr=1e-4,weight_decay=1e-5)

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

1 vote330 views1 answer
Plt imshow python
Python
0 vote286 views1 answer
How to multi thread python
Python
60 votes302 views4 answers
Datetime year python
Python
1 vote299 views2 answers
Lastindexof python
Python
0 vote314 views1 answer
Python reduce function to sum array
Python
0 vote294 views1 answer
Tkinter filedialog how to show more than one filetype
Python
4 votes291 views1 answer
Python random true false
Python
0 vote304 views1 answer
Tree recursive function
Python
32 votes356 views6 answers
Get list of folders in directory python
Python
0 vote285 views1 answer
Python create tuple from input
Python