You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2019/01/11 12:58:09 UTC

[GitHub] ThomasDelteil commented on issue #9612: CUDNN_STATUS_SUCCESS (4 vs. 0) cuDNN: CUDNN_STATUS_INTERNAL_ERROR on jetson TX2

ThomasDelteil commented on issue #9612: CUDNN_STATUS_SUCCESS (4 vs. 0) cuDNN: CUDNN_STATUS_INTERNAL_ERROR on jetson TX2
URL: https://github.com/apache/incubator-mxnet/issues/9612#issuecomment-453509004
 
 
   I get the same error, AUTOTUNE generate out of memory. 
   I tried setting the `workspace="10"` attribute on my convolutions and it does not seem respected as I get the same type of memory allocation, has this been noticed by anybody else?
   By not respected I mean I see the peak allocation that seems to be always at the same peak, though during the autotune the usage seems to remain actually a bit smaller.
   @KellenSunderland 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services