Hi Abhimanyu, Have you try giving the JVM a larger heap memory, e.g. pio deploy -- --driver-memory 4g
Regards, Donald On Tue, Aug 29, 2017 at 9:06 AM, Abhimanyu Nagrath < abhimanyunagr...@gmail.com> wrote: > Hi , > I am new to predictionIo I am using template https://github.com/ > alexice/template-scala-parallel-svd-item-similarity. I have 403K items to > train which contains 7 Numerical fields 5 categorical fields in my > engine.json I have set dimension:500 .and System COnfig is (30 GB RAM , 4 > Cores). after build and training at the time of deploying I am getting the > error : > [ERROR] [LocalFSModels] Requested array size exceeds VM limit > [ERROR] [OneForOneStrategy] None.get > > Any suggestion how to resolve this error. > > > Regards, > Abhimanyu > >