NRauschmayr commented on issue #13113: MXNet TensorRT generates wrong results URL: https://github.com/apache/incubator-mxnet/issues/13113#issuecomment-439632348 I am closing this issue because of https://github.com/apache/incubator-mxnet/pull/13310/files . Thanks Kellen for your help and for fixing this so quickly! Just to give a brief summary of some offline discussions between me and Kellen: Initially I reported that I got values in the order of ^30 or NaN. It turns out that I was running on a GPU model that was not supported. When switching to a p3 instance, I got more reasonably looking results, but feature vectors would still differ quite a bit. In a very few cases this difference would lead to a mispredicted class. I tested the [update](https://github.com/apache/incubator-mxnet/pull/13310/files) on Resnet and Densenet and I am getting the correct results now.
---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services