KellenSunderland commented on issue #13113: MXNet TensorRT generates wrong results URL: https://github.com/apache/incubator-mxnet/issues/13113#issuecomment-438806215 Just thinking a bit more about batch normalization. After optimization I wonder if we even use batch normalization? It should be fixed values, so I would assume TRT would scale the relevant params at engine build time and then not even run batch normalization at runtime.
---------------------------------------------------------------- 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: [email protected] With regards, Apache Git Services
