Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Meaning of mix_activations #79

Open
amueller opened this issue Jan 4, 2024 · 0 comments
Open

Meaning of mix_activations #79

amueller opened this issue Jan 4, 2024 · 0 comments

Comments

@amueller
Copy link
Contributor

amueller commented Jan 4, 2024

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:

config["mix_activations"] = False # False heisst eig True

which seems to imply True and False are switched.
Can you confirm that the comment is out of date, or am I missing something?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@amueller