TastyPancakes/Flux.jl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Minor changes to docstring according to guidelines

Browse Source
This commit is contained in:
Shreyas 2019-03-30 00:28:23 +05:30
parent b6fcd1d837
commit 4cb7b9278b
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/layers/normalise.jl
View File

@ -291,14 +291,14 @@ end
Group Normalization. Group Normalization.
This layer can outperform Batch-Normalization and Instance-Normalization. This layer can outperform Batch-Normalization and Instance-Normalization.
GroupNorm(chs::Integer, G::Integer, λ = identity; GroupNorm(chs::Integer, G::Integer, λ = identity;
initβ = (i) -> zeros(Float32, i), initγ = (i) -> ones(Float32, i), initβ = (i) -> zeros(Float32, i), initγ = (i) -> ones(Float32, i),
ϵ = 1f-5, momentum = 0.1f0) ϵ = 1f-5, momentum = 0.1f0)
chs is the number of channels, the channel dimension of your input. ``chs`` is the number of channels, the channel dimension of your input.
For an array of N dimensions, the (N-1)th index is the channel dimension. For an array of N dimensions, the (N-1)th index is the channel dimension.
G is the number of groups along which the statistics would be computed. ``G`` is the number of groups along which the statistics would be computed.
The number of channels must be an integer multiple of the number of groups. The number of channels must be an integer multiple of the number of groups.
Example: Example:
@ -391,4 +391,4 @@ function Base.show(io::IO, l::GroupNorm)
print(io, "GroupNorm($(join(size(l.β), ", "))") print(io, "GroupNorm($(join(size(l.β), ", "))")
(l.λ == identity) || print(io, ", λ = $(l.λ)") (l.λ == identity) || print(io, ", λ = $(l.λ)")
print(io, ")") print(io, ")")
end end