Label Smoothing applied in Focal Loss
This code is based on the below papers.
criteria = FocalLossWithSmoothing(num_classes)
logits = model(inputs)
loss = criteria(logits, labels)
optim.zero_grad()
loss.backward()
optim.step()
-
Notifications
You must be signed in to change notification settings - Fork 1
Label Smoothing applied in Focal Loss
License
Kageshimasu/focal-loss-with-smoothing
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Label Smoothing applied in Focal Loss
Topics
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published