Arcface loss is a loss function in face recognition. For face recognition, there is also a commonly used loss function centerloss, but centerloss has a relatively large defect, that is, when there are more categories, GPU memory requirements are relatively high, which is more expensive. And the effect of arcface loss is better than centerloss, becauseThe former is based on angle, while the latter is based on distance,For classification, the impact of arcfaceloss is more direct.
-
Notifications
You must be signed in to change notification settings - Fork 0
R4j4n/Realization-of-arcface-loss-function-on-mnist-dataset
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
No description or website provided.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published