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

tweak batchnorm example

Browse Source
This commit is contained in:
Mike J Innes 2017-12-08 19:34:34 +00:00
parent de69d23901
commit 86097e76fd
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/layers/normalisation.jl
View File

@ -81,13 +81,12 @@ in order to normalize the input of other layer,
put the `BatchNorm` layer before activation function. put the `BatchNorm` layer before activation function.
```julia ```julia
julia> m = Chain( m = Chain(
Dense(28^2, 64), Dense(28^2, 64),
BatchNorm(64, λ = relu), BatchNorm(64, λ = relu),
Dense(64, 10), Dense(64, 10),
BatchNorm(10), BatchNorm(10),
softmax) softmax)
Chain(Dense(784, 64), BatchNorm(64, λ = NNlib.relu), Dense(64, 10), BatchNorm(10), NNlib.softmax)
``` ```
""" """
mutable struct BatchNorm{F,V,N} mutable struct BatchNorm{F,V,N}