[BUG] GLVQ training is unstable
GLVQ training is unstable when prototypes are initialized exactly to datapoints without small shifts. Perhaps because of zero distances?
This commit is contained in:
parent
e686adbea1
commit
9a7d3192c0
@ -111,7 +111,8 @@ class StratifiedSelectionInitializer(ClassAwareInitializer):
|
||||
samples_list = [init.generate(per_class) for init in self.initializers]
|
||||
samples = torch.vstack(samples_list)
|
||||
if self.noise is not None:
|
||||
samples = self.add_noise(samples)
|
||||
# samples = self.add_noise(samples)
|
||||
samples = samples + self.noise
|
||||
return samples
|
||||
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user