dmlc / MXNet.jl

MXNet Julia Package - flexible and efficient deep learning in Julia

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Port Executor Manager to Julia

vchuravy opened this issue · comments

For full Module support we will need to port the Python Executor Managers to Julia.

The need to support automatic data parallelism seem to be the source that makes a lot of things very complicated (e.g. the existence of an executor manager). I'm wondering maybe we could have a cleaner and easier interface if we give up the auto data-par feature. (Just a random thought)