run deepstream application on gtx 1080 ti

[fadsamo]

hello dear friend,thank you so much for your excellent work.
My question is how can i implement this project on a nvidia gtx 1080 ti card?
i get following errors when i make file:

  rm -rf src/deepstream_centerface_app.o ds-centerface
  cd custom_parsers/nvds_customparser_centerface && make clean
  make[1]: Entering directory '/home/dariushdl/Centerface-Deepstream/custom_parsers/nvds_customparser_centerface'
  rm -rf libnvds_infercustomparser_centerface.so
  make[1]: Leaving directory '/home/dariushdl/Centerface-Deepstream/custom_parsers/nvds_customparser_centerface'
  g++ -std=c++17 -c -o src/deepstream_centerface_app.o -I/opt/nvidia/deepstream/deepstream-5.0/sources/includes -DDS_VERSION_MINOR=1 -DDS_VERSION_MAJOR=5 `pkg-config --cflags gstreamer-1.0 opencv4` src/deepstream_centerface_app.cpp
  cd custom_parsers/nvds_customparser_centerface && make
  Package opencv4 was not found in the pkg-config search path.
  Perhaps you should add the directory containing `opencv4.pc'
  to the PKG_CONFIG_PATH environment variable
  No package 'opencv4' found
  make[1]: Entering directory '/home/dariushdl/Centerface-Deepstream/custom_parsers/nvds_customparser_centerface'
  g++ -std=c++17 -o libnvds_infercustomparser_centerface.so nvdsinfer_custombboxparser_centerface.cpp -Wall -O3 -shared -fPIC -I/opt/nvidia/deepstream/deepstream-5.1/sources/includes -I/usr/local/cuda/include -Wl,--start-group -lnvinfer -lnvparsers -Wl,--end-group
  In file included from src/deepstream_centerface_app.cpp:1:
  src/deepstream_centerface_app.hpp:2:10: fatal error: gst/gst.h: No such file or directory
      2 | #include <gst/gst.h>
        |          ^~~~~~~~~~~
  compilation terminated.
  make: *** [Makefile:48: src/deepstream_centerface_app.o] Error 1
  make: *** Waiting for unfinished jobs....
  nvdsinfer_custombboxparser_centerface.cpp:8:10: fatal error: nvdsinfer_custom_impl.h: No such file or directory
      8 | #include "nvdsinfer_custom_impl.h"
        |          ^~~~~~~~~~~~~~~~~~~~~~~~~
  compilation terminated.
  make[1]: *** [Makefile:18: libnvds_infercustomparser_centerface.so] Error 1
  make[1]: Leaving directory '/home/dariushdl/Centerface-Deepstream/custom_parsers/nvds_customparser_centerface'
  make: *** [Makefile:54: centerface] Error 2

and my second question is how do this for multiple rtsp cameras?

thank you so much in advance!

[kingardor]

You can fix this by installing opencv

sudo apt install libopencv-dev

To run multiple sources, please add the paths in inputsources.txt

[fadsamo]

Thanks for your reply.
I have successfully detected 10 rtsp cameras simultaneously, but the problem is that some cameras cause a lot of latency ...
My second question is that I want to save the faces that are detected by each id on my computer. But how can I do this and which part of the code should I change?
thank you

[LUOQING1994]

Thanks for your reply.
I have successfully detected 10 rtsp cameras simultaneously, but the problem is that some cameras cause a lot of latency ...
My second question is that I want to save the faces that are detected by each id on my computer. But how can I do this and which part of the code should I change?
thank you

You can refer to the examples of C + + version or Python version provided by deep stream 5.1.

[wareziom]

Thanks for your reply.
I have successfully detected 10 rtsp cameras simultaneously, but the problem is that some cameras cause a lot of latency ...
My second question is that I want to save the faces that are detected by each id on my computer. But how can I do this and which part of the code should I change?
thank you

You can refer to the examples of C + + version or Python version provided by deep stream 5.1.

Can you help me?
I need to save the faces in the file system after face detection and use them for the face recognition system on the next stage.
The only problem is that I want to save only one face from the unique id.
What codes should I change here?

[kingardor]

@wareziom @dariushpt please try the sample under -

/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-image-meta-test