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

Scale and Bias Layers #3591

Merged
merged 2 commits into from
Jan 27, 2016
Merged

Scale and Bias Layers #3591

merged 2 commits into from
Jan 27, 2016

Commits on Jan 22, 2016

  1. Add ChannelwiseAffine for batch norm

    @ducha-aiki @jeffdonahue
    ducha-aiki authored and jeffdonahue committed Jan 22, 2016
    Configuration menu
    Copy the full SHA
    ec04197 View commit details
    Browse the repository at this point in the history

Commits on Jan 23, 2016

  1. Separation and generalization of ChannelwiseAffineLayer into BiasLayer 

    and ScaleLayer.  The behavior of ChannelwiseAffineLayer can be
reproduced by a ScaleLayer with `scale_param { bias_term: true }`.

BiasLayer and ScaleLayer each take 1 or 2 bottoms, with the output having
the same shape as the first.  The second input -- either another  bottom or a
learned parameter -- will have its axes (virtually) broadcast and tiled to have
the same shape as the first, after which elementwise addition (Bias) or
multiplication (Scale) is performed.
    @jeffdonahue
    jeffdonahue committed Jan 23, 2016
    Configuration menu
    Copy the full SHA
    0816907 View commit details
    Browse the repository at this point in the history