mark dropout_mask as non-differentiable

Author: ToucheSir

src/layers/normalise.jl

@@ -55,6 +55,9 @@ function _dropout_mask(rng, x, p; dims=:)
   return y
 end
 
+# TODO move this to NNlib
+Zygote.ChainRulesCore.@non_differentiable dropout_mask(rng, x, p)
+
 """
     Dropout(p; dims=:, rng = rng_from_array())
 

test/layers/normalisation.jl

@@ -273,7 +273,7 @@ end
       x = reshape(collect(1:prod(sizes)), sizes)
 
     @test Flux.hasaffine(m) == true
-    @test length(Flux.params(m)) == 2  
+    @test length(Flux.params(m)) == 2
     x = Float64.(x)
     y = m(x)
     μ = mean(x, dims=1)
@@ -287,7 +287,7 @@ end
       x = reshape(collect(1:prod(sizes)), sizes)
     @test Flux.hasaffine(m) == false
     @test length(Flux.params(m)) == 0
-    
+
     x = Float64.(x)
     y = m(x)
     μ = mean(x, dims=1)
@@ -458,3 +458,8 @@ end
     @test BN(x) ≈ GN(x)
   end
 end
+
+@testset "second derivatives" begin
+  m1 = Dropout(0.5)
+  @test Zygote.hessian_reverse(sum∘m1, [1.0,2.0,3.0]) == ones(3, 3)
+end