Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU):4070ti
• DeepStream Version:6.3
• TensorRT Version:8.5
Please provide the following information when requesting support.
• Hardware (T4/V100/Xavier/Nano/etc) : 4070ti
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) : facenet, fpenet
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here): 5.5.0
Hi,
I’ve compiled the code using the following make file:
CUDA_VER?=
ifeq ($(CUDA_VER),)
$(error "CUDA_VER is not set")
endif
APP:= FR-APP
CC = g++
TARGET_DEVICE = $(shell gcc -dumpmachine | cut -f1 -d -)
NVDS_VERSION:=6.3
LIB_INSTALL_DIR?=/opt/nvidia/deepstream/deepstream-$(NVDS_VERSION)/lib/
APP_INSTALL_DIR?=/opt/nvidia/deepstream/deepstream-$(NVDS_VERSION)/bin/
FACIAL_LANDMARKS_LIB_DIR?=/opt/nvidia/deepstream/deepstream-$(NVDS_VERSION)/lib/cvcore_lib/
#SRCS:= $(wildcard *.cpp)
SRCS:=src/fr_app.cpp src/fr_meta.cpp src/ds_yml_parse.cpp
#INCS:= $(wildcard *.hpp)
PKGS:= gstreamer-1.0 gstreamer-rtsp-server-1.0
OBJS:= $(SRCS:.cpp=.o)
CFLAGS+=-I/opt/nvidia/deepstream/deepstream-$(NVDS_VERSION)/sources/includes \
-I/opt/nvidia/deepstream/deepstream-$(NVDS_VERSION)/sources/includes/cvcore_headers \
-I/usr/local/cuda-$(CUDA_VER)/include \
-I/opt/nvidia/deepstream/deepstream-$(NVDS_VERSION)/sources/apps/apps-common/includes/ \
-I ../common \
-I./inc/ -I/usr/include/opencv4/ -I/usr/local/include -I/home/eegrab/TensorRT/include/
CFLAGS+= $(shell pkg-config --cflags $(PKGS))
CFLAGS+= -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations
LIBS:= $(shell pkg-config --libs $(PKGS))
LIBS+=-L/usr/local/cuda-$(CUDA_VER)/lib64/ -lcudart -lnvdsgst_helper -lm \
-L$(LIB_INSTALL_DIR) -lnvdsgst_meta -lstdc++ -lyaml-cpp -lnvds_meta -lnvds_yml_parser \
-lnvbufsurface -lnvbufsurftransform -lnvds_batch_jpegenc \
-lopencv_core -lopencv_highgui -lopencv_imgproc\
-lcuda -Wl,-rpath,$(LIB_INSTALL_DIR)\
-lpaho-mqttpp3 -lpaho-mqtt3c \
-L/opt/nvidia/deepstream/deepstream-$(NVDS_VERSION)/lib/cvcore_libs
LIBS+=-L$(FACIAL_LANDMARKS_LIB_DIR) -lnvcv_faciallandmarks -lnvcv_core -lnvcv_tensorops -lnvcv_trtbackend
# LIBS+= -lpaho-mqtt3c -lpaho-mqtt3as
all: $(APP)
%.o: %.cpp $(INCS) Makefile
$(CC) -c -g -o $@ $(CFLAGS) -fPIC -Wno-write-strings $<
$(APP): $(OBJS) Makefile
$(CC) -g -o $(APP) $(OBJS) $(LIBS) -lstdc++
install: $(APP) cp -rv $(APP) $(APP_INSTALL_DIR)
clean:
rm -rf $(OBJS) $(APP)
It had compiled without any error. However while i run the app ./FR-APP ./models/fr_app_config.yml there is an error as:
/FR-APP: error while loading shared libraries: libnvcv_faciallandmarks.so: cannot open shared object file: No such file or directory
My local path for libnvcv_faciallandmarks.so is at :
/opt/nvidia/deepstream/deepstream-6.3/lib/cvcore_libs/libnvcv_faciallandmarks.so
Any help on this highly appreciated @junshengy .