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

Minor changes to docstring according to guidelines

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.
This layer can outperform Batch-Normalization and Instance-Normalization.
GroupNorm(chs::Integer, G::Integer, λ = identity;
initβ = (i) -> zeros(Float32, i), initγ = (i) -> ones(Float32, i),
ϵ = 1f-5, momentum = 0.1f0)
GroupNorm(chs::Integer, G::Integer, λ = identity;
initβ = (i) -> zeros(Float32, i), initγ = (i) -> ones(Float32, i),
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.
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.
Example:
@ -391,4 +391,4 @@ function Base.show(io::IO, l::GroupNorm)
print(io, "GroupNorm($(join(size(l.β), ", "))")
(l.λ == identity) || print(io, ", λ = $(l.λ)")
print(io, ")")
end
end