fumingxing2015 commented on issue #16562: Same model but different time-consuming URL: https://github.com/apache/incubator-mxnet/issues/16562#issuecomment-569024882 > Hi，@fumingxing2015，I meet the same problem.I found the geem compute in convlution is very slow.Both MKL and Openblas are slow. > Do you have any suggestion about this problem. I only set the small values to zero ,this can avoid the speed slow down and keep the accuracy no change.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
