*****************************************************************************
* Copyright (c) 2019 NVIDIA Corporation.  All rights reserved.
*
* NVIDIA Corporation and its licensors retain all intellectual property
* and proprietary rights in and to this software, related documentation
* and any modifications thereto.  Any use, reproduction, disclosure or
* distribution of this software and related documentation without an express
* license agreement from NVIDIA Corporation is strictly prohibited.
*****************************************************************************

This demo shows the performance of deepstream, like flowers classification
by TensorRT inference server in GTC show and the difference is that images input
is changed to video input. Please check the below link:

https://www.youtube.com/watch?v=8bbtAvMAI2c

Pipeline:
filesrc (switch)-> h264parser -> nvv4l2decoder -> nvstreammux -> pgie -> sgie1
-> sgie2-> sgie3 -> nvvideoconvert -> nvdsosd -> (nvtransform) ->nveglglessink


Usage:
- Prepare a folder and put all h264 files in it
- $ make
- $ deepstream-perf-demo <rows num> <columns num> <streams dir>
    Note: It's better rows == columns
