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

Layer normalisation for images #592

Merged
merged 2 commits into from
Feb 5, 2019
Merged

Layer normalisation for images #592

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c6409d7
add support for n-dimensional input to normalise layer
MJ10 Feb 5, 2019
046f7b4
fix std arguments in normalise
MJ10 Feb 5, 2019
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
10 changes: 5 additions & 5 deletions src/layers/stateless.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,12 +40,12 @@ but it is more numerically stable.
logitbinarycrossentropy(logŷ, y) = (1 - y)*logŷ - logσ(logŷ)

"""
normalise(x::AbstractVecOrMat)
normalise(x::AbstractArray, dims::Int=1)

Normalise each column of `x` to mean 0 and standard deviation 1.
Normalises x to mean 0 and standard deviation 1, across the dimensions given by dims. Defaults to normalising over columns.
"""
function normalise(x::AbstractVecOrMat)
μ′ = mean(x, dims = 1)
σ′ = std(x, dims = 1, mean = μ′, corrected=false)
function normalise(x::AbstractArray, dims::Int=1)
μ′ = mean(x, dims = dims)
σ′ = std(x, dims = dims, mean = μ′, corrected=false)
return (x .- μ′) ./ σ′
end