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

Posted to commits@mxnet.apache.org by gi...@git.apache.org on 2017/10/12 06:34:40 UTC

[GitHub] chenbiaolong commented on issue #8222: Different convolution result between MXNet and Tensorflow?

chenbiaolong commented on issue #8222: Different convolution result between MXNet and Tensorflow?
URL: https://github.com/apache/incubator-mxnet/issues/8222#issuecomment-336034335
 
 
   @chinakook  In fact, I don't care the training speed much now. I'm working on optimize the inference speed and handing capacity of my model. We use tensorflow c++ API in deploy, but tensorflow's c++ API is not easy to use, and I can't use multithread processing in a single GPU to improve my handing capacity( a single thread will occupy the whole GPU memory... )
 
----------------------------------------------------------------
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