Skip to content
This repository was archived by the owner on May 21, 2022. It is now read-only.

turn off InputNorm (which is broken anyway) so package can be imported #5

Merged
merged 1 commit into from
May 5, 2017
Merged

turn off InputNorm (which is broken anyway) so package can be imported #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/Transformations.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ import LearnBase: transform, transform!,
learn!
# import StatsBase: logistic, logit
import OnlineStats
import OnlineStats: weight, Weight, BoundedEqualWeight, Variances
import OnlineStats: weight, Weight, BoundedEqualWeight

export
input_node,
Expand Down Expand Up @@ -173,7 +173,7 @@ include("linear.jl")
include("affine.jl")
include("misc.jl")
include("layernorm.jl")
include("inputnorm.jl")
# include("inputnorm.jl")
include("activations.jl")
include("whiten.jl")
include("chain.jl")
Expand Down
3 changes: 3 additions & 0 deletions src/inputnorm.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,9 @@
#=
Similar to Batch Normalization, except online and without the rescaling/skew
y = (a .- μ) ./ σ

TODO: This is currently broken because OnlineStats.Variances no longer
exists.
=#
type InputNorm{T,W<:Weight} <: Transformation
n::Int # maps n --> n
Expand Down