nnlib docs

docs/make.jl

@@ -1,6 +1,6 @@
-using Documenter, Flux
+using Documenter, Flux, NNlib
 
-makedocs(modules=[Flux],
+makedocs(modules=[Flux, NNlib],
          doctest = false,
          format = :html,
          analytics = "UA-36890222-9",

docs/src/models/layers.md

@@ -6,3 +6,18 @@ These core layers form the foundation of almost all neural networks.
 Chain
 Dense
 ```
+
+## Activation Functions
+
+Non-linearities that go between layers of your model. Most of these functions are defined in [NNlib](https://github.com/FluxML/NNlib.jl) but are available by default in Flux.
+
+Note that, unless otherwise stated, activation functions operate on scalars. To apply them to an array you can call `σ.(xs)`, `relu.(xs)` and so on.
+
+```@docs
+σ
+relu
+leakyrelu
+elu
+swish
+softmax
+```

src/layers/basic.jl

@@ -50,8 +50,8 @@ as an `in × N` matrix. The out `y` will be a vector or batch of length `out`.
 
     julia> d(rand(5))
     Tracked 2-element Array{Float64,1}:
-    0.00257447
-    -0.00449443
+      0.00257447
+      -0.00449443
 """
 struct Dense{F,S,T}
   σ::F