Error while running the make file

zhouyuchong / face-recognition-deepstream

Deepstream app use retinaface and arcface for face recognition.

MIT License

55 stars 12 forks source link

Error while running the make file #26

Open asmaaana opened 1 year ago

asmaaana commented 1 year ago

The below error is generated when running the make file in ./face-recognition-deepstream/models/retinaface/nvdsinfer_customparser

g++ -o libnvdsinfer_custom_impl_retinaface.so nvdsparse_retinaface.cpp -Wall -std=c++11 -Wno-error=deprecated-declarations -shared -fPIC -I/opt/nvidia/deepstream/deepstream-6.1/sources/includes -I/usr/local/cuda-11.6/include -shared -Wl,--start-group -lnvinfer_plugin -lnvinfer -lnvparsers -Wl,--end-group nvdsparse_retinaface.cpp:23:10: fatal error: nvdsinfer_custom_impl.h: No such file or directory 23 | #include "nvdsinfer_custom_impl.h" | ^~~~~~~~~ compilation terminated.

zhouyuchong commented 1 year ago

@asmaaana check below

cuda version in makefile
deepstream version in makefile

asmaaana commented 1 year ago

Thank you it worked. "Then set "ip;port;topic" in codes. e.g." from where can i get ip;port;topic values?

zhouyuchong commented 1 year ago

@asmaaana They are kafka configs, ip & port should be configured when you initialize kafka server. More details you can refer to deepstream_python_apps and kafka.

asmaaana commented 12 months ago

As i have understood that this model is written over samples test-4. Is there any specific reason for writing over samples test-4 and not test-2 although it can be used for detection and recognition pipeline? Sorry if this question doesn't make sense but I'm trying to implement a similar pipeline but i'm facing some issues

zhouyuchong commented 12 months ago

@asmaaana test-4 demonstrates how to use kafka to send results out. If you want to build a pipeline just for local purpose, you can simply refer to test-2 or test-3.