Implications of setting SIGCHLD in relation to NIFs
Wed Nov 25 20:53:28 CET 2020
We use caffe + tensor-rt for video processing neural networks. They
are tightly integrated with our video decoding code: it is very
important to run all this in a single process to save memory.
Flussonic unpacks protocols to frames, card decodes video, processes
it and sends output. All this is done in a single process or a
Not easy to debug, running separate process is easier and more
reliable of course.
On Tue, Nov 24, 2020 at 9:07 PM Frank Muller <frank.muller.erl@REDACTED> wrote:
> Hi Max
> Interesting... Can you shed some light on how you integrate Neural Network with Flussonic from a design perspective?
> Do you use an external AI library for that ?
> Le mar. 24 nov. 2020 à 18:40, Max Lapshin <max.lapshin@REDACTED> a écrit :
>> > I'm not sure I would like to have TensorFlow running inside the Erlang VM in the first place.
>> We analyse video streams with neural networks. It is almost impossible
>> and useless to run these things in different processes.
>> Everything is running in same process because of enormous data
>> streams, so it is absolutely ok to run all this inside erlang VM =)
>> However, if your traffic is small, it maybe ok to split into different processes
More information about the erlang-questions