Merge branch 'master' of https://github.com/FluxML/Flux.jl

README.md

@@ -31,8 +31,8 @@ Flux has powerful high-level features, and common architectures can be defined i
 ```julia
 model = Chain(
   Dense(768, 128, σ),
-  LSTM(128, 256)
-  LSTM(256, 128)
+  LSTM(128, 256),
+  LSTM(256, 128),
   Dense(128, 10),
   softmax)
 

docs/src/models/basics.md

@@ -129,7 +129,7 @@ linear2 = linear(3, 2)
 
 model(x) = linear2(σ.(linear1(x)))
 
-model(x) # => 2-element vector
+model(rand(5)) # => 2-element vector
 ```
 
 Another (equivalent) way is to create a struct that explicitly represents the affine layer.