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 eaeab58 commit 933115dCopy full SHA for 933115d
pina/loss/ntk_weighting.py
@@ -28,8 +28,6 @@ def aggregate(self, losses):
28
Weights the losses according to the Neural Tangent Kernel
29
30
:param dict(torch.Tensor) input: The dictionary of losses.
31
- :param alpha(float) input: The parameter alpha that regulates the moving average
32
- between old and new weights.
33
:return: The losses aggregation. It should be a scalar Tensor.
34
:rtype: torch.Tensor
35
0 commit comments