Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
I create a network and set the attributes of dropout to training, but it stills can't utilzed the dropout when using MXNet C++ inference API MXPredForward.
How to enable dropout in MXPredForward?
any suggestion?
I create a network and set the attributes of
dropout
totraining
, but it stills can't utilzed thedropout
when using MXNet C++ inference APIMXPredForward
.How to enable
dropout
in MXPredForward? any suggestion?