Add Flux 0.13 compatibility

[lorenzoh]

Closes #201.

Depends on Flux 0.13 release and FluxML/FluxTraining.jl#103

[lorenzoh]

Apparently this fails on 0.12 due to changes necessary to Embeddings for 0.13. @darsnack do you know what could have caused this and if this means that 0.13 changes to Embedding are not forward compatible?

[darsnack]

This isn't because of Embedding. Parallel(connection, layer) (i.e. a single branch) doesn't wrap the single layer in a tuple. So instead of iterating the tuple as expected, we are iterating the branch itself. On v0.13 this should not be the case.

[darsnack]

Okay this is cause FluxML/Flux.jl#1862 added a type restriction to Parallel that should have probably always been there.

You could either remove 0.12 from the compat, special case 0.12 in the source, or on L50 of models.jl, you can do Tuple(catbackbone[2].layers) in the mapreduce.

[lorenzoh]

Thanks! I'll try the forward-compatible fix so that FastAI.jl can be used with both 0.12 and 0.13