matthias comments

Repositories
Issues
Comments

Results 2 comments of


                                            matthias

Getting NaN loss after some time with DeepAR and NegativeBinomial

Did you try switching back to mxnet-cu101mkl==1.4.1 - I think with that mxnet version you can leave out the hybridize False option. I just stumbled on this on my quest...

Getting NaN loss after some time with DeepAR and NegativeBinomial

> @matthiasanderer, I'm running on IBM Power 9. If I'm not wrong, MKL is for Intel Processors. Sorry that was my copy paste of course only version 1.4.1 is the...