You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
# Multi-class Focal Loss
4
4
5
-
An implementation of Focal Loss, as described in the RetinaNet paper, https://arxiv.org/abs/1708.02002, generalized to the multi-class case.
5
+
An (unofficial) implementation of Focal Loss, as described in the RetinaNet paper, https://arxiv.org/abs/1708.02002, generalized to the multi-class case.
6
6
7
7
It is essentially an enhancement to cross-entropy loss and is useful for classification tasks when there is a large class imbalance. It has the effect of underweighting easy examples.
0 commit comments