Why does my pruned and retrained tao yolov3 model have more GPU memory usage per pipeline than the original unpruned model?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
, ,
12

Hi @adithya.ajith
Does “two pipelines” mean two application?

And, with one application/pipeline, using pruned-network and unpruned network consume the same memory - 479MB.
while using another application/pipeline, using pruned-network consumes more memory than using unpruned network,i.e. 645MB vs 619MB?

Can you refer to DeepStream SDK FAQ - #10 by mchi to dump the pipeline diagram of these two?