My understanding of mix_activations is whether to mix activation functions within a batch when sampling from the MLP prior.
Now there's
if not (('mix_activations' in hyperparameters) and hyperparameters['mix_activations']):
s = hyperparameters['prior_mlp_activations']()
hyperparameters['prior_mlp_activations'] = lambda: s
which seems to support that. Now there's this comment:
My understanding of
mix_activations
is whether to mix activation functions within a batch when sampling from the MLP prior. Now there'swhich seems to support that. Now there's this comment:
which seems to imply
True
andFalse
are switched. Can you confirm that the comment is out of date, or am I missing something?