Deep learning in Julia

[pxl-th]

@simsurace

If anyone who has used both could give examples of models that can be easily built using PyTorch but just hit a brick wall of either problems or productivity in Flux, that would help a lot I think.

For me the brick wall is the lack of proper GPU memory management.
It does not matter if some functionality is missing if you run out of memory on the first training iteration. And most of the building blocks already exist in Julia.