We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent b5981e7 commit f58fd6dCopy full SHA for f58fd6d
segmentation_models_pytorch/losses/tversky.py
@@ -10,7 +10,7 @@
10
11
class TverskyLoss(DiceLoss):
12
"""Tversky loss for image segmentation task.
13
- Where TP and FP is weighted by alpha and beta params.
+ Where FP and FN is weighted by alpha and beta params.
14
With alpha == beta == 0.5, this loss becomes equal DiceLoss.
15
It supports binary, multiclass and multilabel cases
16
0 commit comments