Re:Running your models in production with TensorFlow Serving
by barneso on Tuesday February 16, 2016 @08:59PM
(#11114641)
For profiling of models, almost everything needed is already there. You only need to pass in a StepStatsCollector through the Session::Run() method (I called it RunWithStats() ) and hook it up to the Executor Args by filling in this variable: https://github.com/tensorflow/tensorflow/blob/master/tensorf... You then get a very usable set of profiling statistics out by aggregating the StepStats object. For profiling individual ops on the CPU, perf is very useful.
[ Parent
| on HN ]
There are no comments on this comment yet.