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 3057ef6 commit ec03773Copy full SHA for ec03773
mmseg/models/losses/dice_loss.py
@@ -55,8 +55,6 @@ class DiceLoss(nn.Module):
55
Volumetric Medical Image Segmentation <https://arxiv.org/abs/1606.04797>`_.
56
57
Args:
58
- loss_type (str, optional): Binary or multi-class loss.
59
- Default: 'multi_class'. Options are "binary" and "multi_class".
60
smooth (float): A float number to smooth loss, and avoid NaN error.
61
Default: 1
62
exponent (float): An float number to calculate denominator
0 commit comments