I would like to deploy shadoworflow on a production server. I expect about 200 concurrent users. I will use a parser and some of my own neural network deep learning models. I would like to know the peak of memory and processor for the same.
Appreciate your help.
Trying a simple (but very variable) guess:
If you are talking about deep learning, I suggest that you speak at least 3 or more layers, including some CNN and probably RNN.
2D 3D-, , , , , , GPU.
, .
, , ? .
, , , .
.
3 :
3 , , , : x
. , . Tensorflow, concurrency ,