How to run bpnet in tao toolkit?

Hi,

I could run the detectnet_v2 just fine, thx
Now, I am trying to run bpnet by following, Body Pose Estimation — TAO Toolkit 3.22.05 documentation
http://127.0.0.1:8888/notebooks/cv_samples_vv1.2.0/bpnet/bpnet.ipynb
I have changed the file path
%env LOCAL_PROJECT_DIR=“/home/nvidia/cv_samples_vv1.2.0/bpnet”
%env SAMPLES_DIR=“/home/nvidia/cv_samples_vv1.2.0/bpnet/deps”

But I got this error, I have created a folder called deps, not really sure what I have missed… Sorry I am new to tao toolkits… >_<

# Install requirement

!pip3 install -r $SAMPLES_DIR/deps/requirements-pip.txt

ERROR: Could not open requirements file: [Errno 2] No such file or directory: '"/home/nvidia/cv_samples_vv1.2.0/bpnet/deps"/deps/requirements-pip.txt'

Firstly, please use the latest notebook. Its version is 1.4.1.
The command can be found in TAO Toolkit Quick Start Guide — TAO Toolkit 3.22.05 documentation

ok ok

I have changed the folder link and it works now. Thx
!pip3 install -r /home/nvidia/cv_samples_v1.4.0/deps/requirements-pip.txt

Hi,
I am still looking how to properly download the dataset… The download time is 6hrs… I will let you know if it works. Thx

3. Prepare dataset and pre-trained model

We will be using the COCO (common objects on context) 2017 dataset for this example. To find more details please visit https://cocodataset.org/#keypoints-2017 and https://cocodataset.org/#keypoints-eval. Please download the dataset and extract as per instructions below.

Links to download the data: train_data, val_data and annotations. Please unzip the images into the $LOCAL_DATA_DIR directory and the annotations into the $LOCAL_DATA_DIR/annotations. You may use this notebook with your own dataset as well. To use this example with your own dataset, please refer to Use your own dataset section below.

Hi,

After some tuning, the training is in progress, I will let you know if it is successful.
Thx

Hi,

It is still under training…
May I know how to put the model in the Jetson platform? I have a Orin AGX.
Is there any tutorial?
I am trying to follow this tutorial but fail in tlt-converter… (I use detectnet_v2 as in the video)

Thx

Please refer to Body Pose Estimation — TAO Toolkit 3.22.05 documentation .
and deepstream_tao_apps/apps/tao_others at master · NVIDIA-AI-IOT/deepstream_tao_apps · GitHub

Hi,

It is getting hard to go through these document as I am new to tao toolkits. Is there any tutorial of how to use bpnet in Jetson Orin?
Thx

nvidia@ubuntu:~/deepstream_tao_apps$     cd apps/tao_others
nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others$     cd /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate
nvidia@ubuntu:/opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate$     make
Makefile:25: *** "CUDA_VER is not set".  Stop.
nvidia@ubuntu:/opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate$     cp libnvdsgst_videotemplate.so /opt/nvidia/deepstream/deepstream/lib/gst-plugins/
cp: cannot stat 'libnvdsgst_videotemplate.so': No such file or directory
nvidia@ubuntu:/opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate$     rm -rf ~/.cache/gstreamer-1.0/
nvidia@ubuntu:/opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate$ 

Hi,

I followed this link but still have error

nvidia@ubuntu:/opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate$ CUDA_VER=10.0 make
-fPIC -DDS_VERSION="6.1.0" -I /usr/local/cuda-10.0/include -I ../../includes -I ./includes -std=c++17 -Wall -Werror -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include
g++ -c -o gstnvdsvideotemplate.o -fPIC -DDS_VERSION=\"6.1.0\" -I /usr/local/cuda-10.0/include -I ../../includes -I ./includes -std=c++17 -Wall -Werror -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include gstnvdsvideotemplate.cpp
In file included from gstnvdsvideotemplate.cpp:34:
gstnvdsvideotemplate.h:31:10: fatal error: cuda_runtime.h: No such file or directory
   31 | #include <cuda_runtime.h>
      |          ^~~~~~~~~~~~~~~~
compilation terminated.
make: *** [Makefile:62: gstnvdsvideotemplate.o] Error 1
nvidia@ubuntu:/opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideoooteoooooootemplate$ 

I tune the make and can go through several comand but stuck again…

nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others$     export CUDA_VER=11.4
nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others$     make
make[1]: Entering directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app'
g++ -c -o deepstream_bodypose2d_app.o -fpermissive -Wall -Werror -DPLATFORM_TEGRA -I/opt/nvidia/deepstream/deepstream/sources/includes -I/opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations -std=c++11 deepstream_bodypose2d_app.cpp
g++ -c -o deepstream_bodypose2d_meta.o -Wall -Werror -DPLATFORM_TEGRA -I/opt/nvidia/deepstream/deepstream/sources/includes -I/opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations -std=c++11 deepstream_bodypose2d_meta.cpp
g++ -c -o ds_yml_parse.o -Wall -Werror -DPLATFORM_TEGRA -I/opt/nvidia/deepstream/deepstream/sources/includes -I/opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations -std=c++11 ../common/ds_yml_parse.cpp
cc -o deepstream-bodypose2d-app deepstream_bodypose2d_app.o deepstream_bodypose2d_meta.o ds_yml_parse.o `pkg-config --libs gstreamer-1.0` -L/opt/nvidia/deepstream/deepstream/lib/ -lnvdsgst_meta -lnvds_meta -lnvds_inferutils -lnvds_utils -lm -lstdc++ -lgstrtspserver-1.0 -lnvds_yml_parser -L/opt/nvidia/deepstream/deepstream/lib/cvcore_libs -L/usr/local/cuda-11.4/lib64/ -lcudart -lcuda -lyaml-cpp -lnvcv_bodypose2d -lnvcv_core -lnvcv_tensorops -lnvcv_trtbackend -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib/
make[1]: Leaving directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app'
make[1]: Entering directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-faciallandmark-app'
g++ -c -o deepstream_faciallandmark_app.o -fpermissive -Wall -Werror -DPLATFORM_TEGRA -I/opt/nvidia/deepstream/deepstream/sources/includes -I/opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations deepstream_faciallandmark_app.cpp
g++ -c -o deepstream_faciallandmark_meta.o -Wall -Werror -DPLATFORM_TEGRA -I/opt/nvidia/deepstream/deepstream/sources/includes -I/opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations deepstream_faciallandmark_meta.cpp
g++ -c -o ds_yml_parse.o -Wall -Werror -DPLATFORM_TEGRA -I/opt/nvidia/deepstream/deepstream/sources/includes -I/opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations ../common/ds_yml_parse.cpp
cc -o deepstream-faciallandmark-app deepstream_faciallandmark_app.o deepstream_faciallandmark_meta.o ds_yml_parse.o `pkg-config --libs gstreamer-1.0` -L/opt/nvidia/deepstream/deepstream/lib/ -lnvdsgst_meta -lnvds_meta -lnvds_inferutils -lnvds_utils -lm -lstdc++ -lnvds_yml_parser -lgstrtspserver-1.0 -L/usr/local/cuda-11.4/lib64/ -lcudart -lcuda -lyaml-cpp -L/opt/nvidia/deepstream/deepstream/lib/cvcore_libs -lnvcv_faciallandmarks -lnvcv_core -lnvcv_tensorops -lnvcv_trtbackend -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib/
make[1]: Leaving directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-faciallandmark-app'
make[1]: Entering directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-emotion-app'
g++ -c -o deepstream_emotion_app.o -fpermissive -Wall -Werror -DPLATFORM_TEGRA -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common -I ../deepstream-faciallandmark-app `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations deepstream_emotion_app.cpp
g++ -c -o deepstream_faciallandmark_meta.o -Wall -Werror -DPLATFORM_TEGRA -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common -I ../deepstream-faciallandmark-app `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations ../deepstream-faciallandmark-app/deepstream_faciallandmark_meta.cpp
g++ -c -o ds_yml_parse.o -Wall -Werror -DPLATFORM_TEGRA -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common -I ../deepstream-faciallandmark-app `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations ../common/ds_yml_parse.cpp
cc -o deepstream-emotion-app deepstream_emotion_app.o deepstream_faciallandmark_meta.o ds_yml_parse.o `pkg-config --libs gstreamer-1.0` -L/opt/nvidia/deepstream/deepstream/lib/ -lnvdsgst_meta -lnvds_meta -lnvds_inferutils -lnvds_utils -lm -lstdc++ -lnvds_yml_parser -lgstrtspserver-1.0 -L/usr/local/cuda-11.4/lib64/ -lcudart -lcuda -lyaml-cpp -L/opt/nvidia/deepstream/deepstream/lib/cvcore_libs -lnvcv_faciallandmarks -lnvcv_core -lnvcv_tensorops -lnvcv_trtbackend -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib/
make[1]: Leaving directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-emotion-app'
make[1]: Entering directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-emotion-app/emotion_impl'
-fPIC -DDS_VERSION="6.1.0" -I /usr/local/cuda-11.4/include -I /opt/nvidia/deepstream/deepstream/sources/includes -I../includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I ../../deepstream-faciallandmark-app -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations
g++ -c -o emotion_impl.o -fPIC -DDS_VERSION=\"6.1.0\" -I /usr/local/cuda-11.4/include -I /opt/nvidia/deepstream/deepstream/sources/includes -I../includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I ../../deepstream-faciallandmark-app -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations emotion_impl.cpp
-fPIC -DDS_VERSION="6.1.0" -I /usr/local/cuda-11.4/include -I /opt/nvidia/deepstream/deepstream/sources/includes -I../includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I ../../deepstream-faciallandmark-app -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations
g++ -c -o ../../common/ds_yml_parse.o -fPIC -DDS_VERSION=\"6.1.0\" -I /usr/local/cuda-11.4/include -I /opt/nvidia/deepstream/deepstream/sources/includes -I../includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I ../../deepstream-faciallandmark-app -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations ../../common/ds_yml_parse.cpp
-fPIC -DDS_VERSION="6.1.0" -I /usr/local/cuda-11.4/include -I /opt/nvidia/deepstream/deepstream/sources/includes -I../includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I ../../deepstream-faciallandmark-app -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations
g++ -o libnvds_emotion_impl.so emotion_impl.o ../../common/ds_yml_parse.o -shared -Wl,-no-undefined -lnvds_yml_parser -lgstrtspserver-1.0 -L/usr/local/cuda-11.4/lib64/ -lcudart -ldl -lpthread -lyaml-cpp -L/opt/nvidia/deepstream/deepstream/lib/ -lnvdsgst_helper -lnvdsgst_meta -lnvds_meta -lnvbufsurface -lnvbufsurftransform -lnvdsbufferpool -lnvds_infer -L/opt/nvidia/deepstream/deepstream/lib/cvcore_libs -lnvcv_emotions -lnvcv_core -lnvcv_trtbackend -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib/ -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib//cvcore_libs/ -L/usr/lib/aarch64-linux-gnu/tegra -lgstvideo-1.0 -lgstbase-1.0 -lgstreamer-1.0 -lgobject-2.0 -lglib-2.0
make[1]: Leaving directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-emotion-app/emotion_impl'
make[1]: Entering directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-gaze-app'
g++ -c -o deepstream_gaze_app.o -fpermissive -Wall -Werror -DPLATFORM_TEGRA -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../deepstream-faciallandmark-app -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations deepstream_gaze_app.cpp
g++ -c -o deepstream_faciallandmark_meta.o -Wall -Werror -DPLATFORM_TEGRA -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../deepstream-faciallandmark-app -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations ../deepstream-faciallandmark-app/deepstream_faciallandmark_meta.cpp
g++ -c -o ds_yml_parse.o -Wall -Werror -DPLATFORM_TEGRA -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../deepstream-faciallandmark-app -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations ../common/ds_yml_parse.cpp
cc -o deepstream-gaze-app deepstream_gaze_app.o deepstream_faciallandmark_meta.o ds_yml_parse.o `pkg-config --libs gstreamer-1.0` -L/opt/nvidia/deepstream/deepstream/lib/ -lnvdsgst_meta -lnvds_meta -lnvds_inferutils -lnvds_utils -lm -lstdc++ -lnvds_yml_parser -lgstrtspserver-1.0 -L/usr/local/cuda-11.4/lib64/ -lcudart -lcuda -lyaml-cpp -L/opt/nvidia/deepstream/deepstream/lib/cvcore_libs -lnvcv_faciallandmarks -lnvcv_core -lnvcv_tensorops -lnvcv_trtbackend -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib/
make[1]: Leaving directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-gaze-app'
make[1]: Entering directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-gaze-app/gazeinfer_impl'
-fPIC -DDS_VERSION="6.1.0" -I /usr/local/cuda-11.4/include -I ../../../includes -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I ../../deepstream-faciallandmark-app -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations
g++ -c -o gazeinfer.o -fPIC -DDS_VERSION=\"6.1.0\" -I /usr/local/cuda-11.4/include -I ../../../includes -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I ../../deepstream-faciallandmark-app -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations gazeinfer.cpp
gazeinfer.cpp: In member function ‘void GazeAlgorithm::OutputThread()’:
gazeinfer.cpp:841:18: warning: narrowing conversion of ‘((GazeAlgorithm*)this)->GazeAlgorithm::m_batch_width’ from ‘int’ to ‘uint32_t’ {aka ‘unsigned int’} [-Wnarrowing]
  841 |           {0, 0, m_batch_width, m_batch_height};
      |                  ^~~~~~~~~~~~~
gazeinfer.cpp:841:33: warning: narrowing conversion of ‘((GazeAlgorithm*)this)->GazeAlgorithm::m_batch_height’ from ‘int’ to ‘uint32_t’ {aka ‘unsigned int’} [-Wnarrowing]
  841 |           {0, 0, m_batch_width, m_batch_height};
      |                                 ^~~~~~~~~~~~~~
-fPIC -DDS_VERSION="6.1.0" -I /usr/local/cuda-11.4/include -I ../../../includes -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I ../../deepstream-faciallandmark-app -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations
g++ -c -o deepstream_gaze_meta.o -fPIC -DDS_VERSION=\"6.1.0\" -I /usr/local/cuda-11.4/include -I ../../../includes -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I ../../deepstream-faciallandmark-app -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations deepstream_gaze_meta.cpp
-fPIC -DDS_VERSION="6.1.0" -I /usr/local/cuda-11.4/include -I ../../../includes -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I ../../deepstream-faciallandmark-app -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations
g++ -o libnvds_gazeinfer.so gazeinfer.o deepstream_gaze_meta.o ../../common/ds_yml_parse.o -shared -Wl,-no-undefined -L/usr/local/cuda-11.4/lib64/ -lcudart -lcuda -ldl -lpthread -lyaml-cpp -L/opt/nvidia/deepstream/deepstream/lib/ -lnvdsgst_helper -lnvdsgst_meta -lnvds_meta -lnvds_yml_parser -L/opt/nvidia/deepstream/deepstream/lib/cvcore_libs -lnvds_infer -lgstrtspserver-1.0 -lnvbufsurface -lnvbufsurftransform -lnvdsbufferpool -lnvcv_core -lnvcv_gazenet -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib/ -L/usr/lib/aarch64-linux-gnu/tegra -lgstvideo-1.0 -lgstbase-1.0 -lgstreamer-1.0 -lgobject-2.0 -lglib-2.0
make[1]: Leaving directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-gaze-app/gazeinfer_impl'
make[1]: Entering directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-gesture-app'
g++ -c -o deepstream_gesture_app.o -DPLATFORM_TEGRA -I/opt/nvidia/deepstream/deepstream/sources/includes -I/opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../deepstream-bodypose2d-app -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations deepstream_gesture_app.c
deepstream_gesture_app.c: In function ‘GstPadProbeReturn sgie_sink_pad_buffer_probe(GstPad*, GstPadProbeInfo*, gpointer)’:
deepstream_gesture_app.c:571:39: warning: narrowing conversion of ‘rect_params._NvOSD_RectParams::left’ from ‘float’ to ‘int’ [-Wnarrowing]
  571 |         cvcore::BBox bbox{rect_params.left, rect_params.top,
      |                           ~~~~~~~~~~~~^~~~
deepstream_gesture_app.c:571:57: warning: narrowing conversion of ‘rect_params._NvOSD_RectParams::top’ from ‘float’ to ‘int’ [-Wnarrowing]
  571 |         cvcore::BBox bbox{rect_params.left, rect_params.top,
      |                                             ~~~~~~~~~~~~^~~
deepstream_gesture_app.c:572:28: warning: narrowing conversion of ‘(rect_params._NvOSD_RectParams::left + rect_params._NvOSD_RectParams::width)’ from ‘float’ to ‘int’ [-Wnarrowing]
  572 |           rect_params.left + rect_params.width, rect_params.top +
      |           ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~
deepstream_gesture_app.c:572:65: warning: narrowing conversion of ‘(rect_params._NvOSD_RectParams::top + rect_params._NvOSD_RectParams::height)’ from ‘float’ to ‘int’ [-Wnarrowing]
  572 |           rect_params.left + rect_params.width, rect_params.top +
      |                                                 ~~~~~~~~~~~~~~~~^
  573 |             rect_params.height};
      |             ~~~~~~~~~~~~~~~~~~                                   
g++ -o deepstream-gesture-app deepstream_gesture_app.o ../deepstream-bodypose2d-app/deepstream_bodypose2d_meta.o ../common/ds_yml_parse.o `pkg-config --libs gstreamer-1.0` -L/opt/nvidia/deepstream/deepstream/lib/ -lnvdsgst_meta -lnvds_meta -lnvds_inferutils -lnvds_utils -lm -lstdc++ -lnvds_yml_parser -lgstrtspserver-1.0 -L/opt/nvidia/deepstream/deepstream/lib/cvcore_libs -L/usr/local/cuda-11.4/lib64/ -lcudart -lcuda -lyaml-cpp -lnvcv_bodypose2d -lnvcv_core -lnvcv_tensorops -lnvcv_trtbackend -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib/
make[1]: Leaving directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-gesture-app'
make[1]: Entering directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-heartrate-app/heartrateinfer_impl'
-fPIC -DDS_VERSION="6.1.0" -I /usr/local/cuda-11.4/include -I ../../../includes -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations
g++ -c -o heartrateinfer.o -fPIC -DDS_VERSION=\"6.1.0\" -I /usr/local/cuda-11.4/include -I ../../../includes -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations heartrateinfer.cpp
heartrateinfer.cpp: In member function ‘void HeartRateAlgorithm::OutputThread()’:
heartrateinfer.cpp:840:18: warning: narrowing conversion of ‘((HeartRateAlgorithm*)this)->HeartRateAlgorithm::m_batch_width’ from ‘int’ to ‘uint32_t’ {aka ‘unsigned int’} [-Wnarrowing]
  840 |           {0, 0, m_batch_width, m_batch_height};
      |                  ^~~~~~~~~~~~~
heartrateinfer.cpp:840:33: warning: narrowing conversion of ‘((HeartRateAlgorithm*)this)->HeartRateAlgorithm::m_batch_height’ from ‘int’ to ‘uint32_t’ {aka ‘unsigned int’} [-Wnarrowing]
  840 |           {0, 0, m_batch_width, m_batch_height};
      |                                 ^~~~~~~~~~~~~~
heartrateinfer.cpp:886:38: warning: narrowing conversion of ‘rect_params._NvOSD_RectParams::left’ from ‘float’ to ‘int’ [-Wnarrowing]
  886 |           faceBBox[0] = {rect_params.left, rect_params.top,
      |                          ~~~~~~~~~~~~^~~~
heartrateinfer.cpp:886:56: warning: narrowing conversion of ‘rect_params._NvOSD_RectParams::top’ from ‘float’ to ‘int’ [-Wnarrowing]
  886 |           faceBBox[0] = {rect_params.left, rect_params.top,
      |                                            ~~~~~~~~~~~~^~~
heartrateinfer.cpp:887:38: warning: narrowing conversion of ‘(rect_params._NvOSD_RectParams::left + rect_params._NvOSD_RectParams::width)’ from ‘float’ to ‘int’ [-Wnarrowing]
  887 |                     rect_params.left + rect_params.width,
      |                     ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~
heartrateinfer.cpp:888:37: warning: narrowing conversion of ‘(rect_params._NvOSD_RectParams::top + rect_params._NvOSD_RectParams::height)’ from ‘float’ to ‘int’ [-Wnarrowing]
  888 |                     rect_params.top + rect_params.height};
      |                     ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~
-fPIC -DDS_VERSION="6.1.0" -I /usr/local/cuda-11.4/include -I ../../../includes -I /opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-nvdsvideotemplate/includes -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I ../ -I ../../common/ -pthread -I/usr/include/gstreamer-1.0 -I/usr/include/orc-0.4 -I/usr/include/gstreamer-1.0 -I/usr/include/glib-2.0 -I/usr/lib/aarch64-linux-gnu/glib-2.0/include -Wno-deprecated-declarations
g++ -o libnvds_heartrateinfer.so heartrateinfer.o ../../common/ds_yml_parse.o -shared -Wl,-no-undefined -lnvds_yml_parser -lgstrtspserver-1.0 -L/usr/local/cuda-11.4/lib64/ -lcudart -lcuda -ldl -lpthread -L/opt/nvidia/deepstream/deepstream/lib/ -lnvdsgst_helper -lnvdsgst_meta -lnvds_meta -lnvds_infer -L/opt/nvidia/deepstream/deepstream/lib/cvcore_libs -lyaml-cpp -lnvbufsurface -lnvbufsurftransform -lnvdsbufferpool -lnvcv_core -lnvcv_heartrate -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib/ -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib/cvcore_libs/ -L/usr/lib/aarch64-linux-gnu/tegra -lgstvideo-1.0 -lgstbase-1.0 -lgstreamer-1.0 -lgobject-2.0 -lglib-2.0
make[1]: Leaving directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-heartrate-app/heartrateinfer_impl'
make[1]: Entering directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-heartrate-app'
g++ -c -o deepstream_heartrate_app.o -fpermissive -Wall -Werror -DPLATFORM_TEGRA -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations deepstream_heartrate_app.cpp
g++ -c -o ds_yml_parse.o -Wall -Werror -DPLATFORM_TEGRA -I /opt/nvidia/deepstream/deepstream/sources/includes -I /opt/nvidia/deepstream/deepstream/sources/includes/cvcore_headers -I /usr/local/cuda-11.4/include -I ../common `pkg-config --cflags gstreamer-1.0` -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-sign-compare -Wno-deprecated-declarations ../common/ds_yml_parse.cpp
cc -o deepstream-heartrate-app deepstream_heartrate_app.o ds_yml_parse.o `pkg-config --libs gstreamer-1.0` -L/opt/nvidia/deepstream/deepstream/lib/ -lnvdsgst_meta -lnvds_meta -lnvds_inferutils -lnvds_utils -lm -lstdc++ -lnvds_yml_parser -lgstrtspserver-1.0 -L/usr/local/cuda-11.4/lib64/ -lcudart -lcuda -lyaml-cpp -L/opt/nvidia/deepstream/deepstream/lib/cvcore_libs -lnvcv_faciallandmarks -lnvcv_core -lnvcv_tensorops -lnvcv_trtbackend -Wl,-rpath,/opt/nvidia/deepstream/deepstream/lib/
make[1]: Leaving directory '/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-heartrate-app'
nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others$     export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/nvidia/deepstream/deepstream/lib/cvcore_libs
nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others$  cd deepstream-bodypose2d-app
nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app$ ./deepstream-bodypose2d-app 1 ../../../configs/bodypose2d_tao/sample_bodypose2d_model_config.txt 0 0 file:///usr/data/bodypose2d_test.png ./body2dout

(gst-plugin-scanner:15202): GStreamer-WARNING **: 16:29:49.954: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_inferserver.so': libtritonserver.so: cannot open shared object file: No such file or directory

(gst-plugin-scanner:15202): GStreamer-WARNING **: 16:29:49.969: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_udp.so': librivermax.so.0: cannot open shared object file: No such file or directory
Request sink_0 pad from streammux
joint Edges 1 , 8
joint Edges 8 , 9
joint Edges 9 , 10
joint Edges 1 , 11
joint Edges 11 , 12
joint Edges 12 , 13
joint Edges 1 , 2
joint Edges 2 , 3
joint Edges 3 , 4
joint Edges 2 , 16
joint Edges 1 , 5
joint Edges 5 , 6
joint Edges 6 , 7
joint Edges 5 , 17
joint Edges 1 , 0
joint Edges 0 , 14
joint Edges 0 , 15
joint Edges 14 , 16
joint Edges 15 , 17
connections 0 , 1
connections 1 , 2
connections 1 , 5
connections 2 , 3
connections 3 , 4
connections 5 , 6
connections 6 , 7
connections 2 , 8
connections 8 , 9
connections 9 , 10
connections 5 , 11
connections 11 , 12
connections 12 , 13
connections 0 , 14
connections 14 , 16
connections 8 , 11
connections 15 , 17
connections 0 , 15
Now playing: file:///usr/data/bodypose2d_test.png
WARNING: Deserialize engine failed because file path: /home/nvidia/deepstream_tao_apps/configs/bodypose2d_tao/../../models/bodypose2d/model.etlt_b32_gpu0_fp16.engine open error
0:00:05.148199758 15201 0xaaaae3449e00 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1888> [UID = 1]: deserialize engine from file :/home/nvidia/deepstream_tao_apps/configs/bodypose2d_tao/../../models/bodypose2d/model.etlt_b32_gpu0_fp16.engine failed
0:00:05.304385506 15201 0xaaaae3449e00 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1993> [UID = 1]: deserialize backend context from engine from file :/home/nvidia/deepstream_tao_apps/configs/bodypose2d_tao/../../models/bodypose2d/model.etlt_b32_gpu0_fp16.engine failed, try rebuild
0:00:05.304678340 15201 0xaaaae3449e00 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: onnx2trt_utils.cpp:363: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
WARNING: [TRT]: DLA requests all profiles have same min, max, and opt value. All dla layers are falling back to GPU

0:11:05.334551750 15201 0xaaaae3449e00 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1946> [UID = 1]: serialize cuda engine to file: /home/nvidia/deepstream_tao_apps/models/bodypose2d/model.etlt_b32_gpu0_fp16.engine successfully
INFO: [FullDims Engine Info]: layers num: 3
0   INPUT  kFLOAT input_1:0       288x384x3       min: 1x288x384x3     opt: 32x288x384x3    Max: 32x288x384x3    
1   OUTPUT kFLOAT heatmap_out/BiasAdd:0 36x48x19        min: 0               opt: 0               Max: 0               
2   OUTPUT kFLOAT conv2d_transpose_1/BiasAdd:0 144x192x38      min: 0               opt: 0               Max: 0               

0:11:06.277470953 15201 0xaaaae3449e00 INFO                 nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary-infer-engine1> [UID 1]: Load new model:../../../configs/bodypose2d_tao/bodypose2d_pgie_config.txt sucessfully
Decodebin child added: source
Decodebin child added: decodebin0
Running...
ERROR from element source: Resource not found.
Error details: gstfilesrc.c(532): gst_file_src_start (): /GstPipeline:pipeline/GstBin:source-bin-00/GstURIDecodeBin:uri-decode-bin/GstFileSrc:source:
No such file "/usr/data/bodypose2d_test.png"
Returned, stopping playback
Average fps 0.000233
Totally 0 persons are inferred
Deleting pipeline
nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app$ 

Hi,

In short, I just want a list of commands so that I can run the bpnet example in my Jetson Orin.
Note: My AGX Orin is new and flashed using SDK manager with deepstream 6.0
Note: My linux desktop has RTX2080 only, the bpnet training is still in progress…

Thx

From your latest log, there is not “/usr/data/bodypose2d_test.png”.
Please check further.

I know, but the png is supposed to be installed, right? I have asked the question in the github also.
I just want to try bpnet training and run on my Orin…
Still looking for a good tutorial link… >_<

This png file is just a demo file.
Could you download another one for testing.
$ wget https://developer-blogs.nvidia.com/wp-content/uploads/2021/06/original-image.png

Hi,

I have downloaded the png, but I have encountered the library problem

nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app$ ./deepstream-bodypose2d-app 1 ../../../configs/bodypose2d_tao/sample_bodypose2d_model_config.txt 0 0 /home/nvidia/Downloads/original-image.png ./body2dout
./deepstream-bodypose2d-app: error while loading shared libraries: libnvcv_bodypose2d.so: cannot open shared object file: No such file or directory

I have looked at this forum but it was 2018 >_<
Not sure how to do it. Or if there is an updated tutorial, I can start all over again. Thx

HI,

I tried again using root, different error, I guess the usage is wrong, is there any example command? Thx

root@ubuntu:/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app# ./deepstream-bodypose2d-app 2 ../../../configs/bodypose2d_tao/sample_bodypose2d_model_config.txt file:///home/nvidia/Downloads/original-image.png ./body2dout
Usage: ./deepstream-bodypose2d-app [1:file sink|2:fakesink|3:display sink|4:rtsp output] <model configure file> <udp port> <rtsp port> <input file> ... <inputfile> <out H264 filename>
OR
./deepstream-bodypose2d-app <yaml config file>

HI,

I tried this command and it runs, but there is no display… still trying to figure it out…

root@ubuntu:/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app# less bodypose2d_app_config.yml 

[1]+  Stopped                 less bodypose2d_app_config.yml
root@ubuntu:/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app# ./deepstream-bodypose2d-app 2 bodypose2d_app_config.yml 
Usage: ./deepstream-bodypose2d-app [1:file sink|2:fakesink|3:display sink|4:rtsp output] <model configure file> <udp port> <rtsp port> <input file> ... <inputfile> <out H264 filename>
OR
./deepstream-bodypose2d-app <yaml config file>
root@ubuntu:/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app# ./deepstream-bodypose2d-app bodypose2d_app_config.yml 
Request sink_0 pad from streammux
Request sink_1 pad from streammux
!! [WARNING] Unknown param found : type
!! [WARNING] Unknown param found : enc
!! [WARNING] Unknown param found : udpport
!! [WARNING] Unknown param found : rtspport
!! [WARNING] Unknown param found : filename
total 1 item
group model-config found 0
Now playing: SUDO_GID=1000
Opening in BLOCKING MODE 
WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
0:00:05.568973856  8978 0xaaaad8d91060 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/home/nvidia/deepstream_tao_apps/models/bodypose2d/model.etlt_b32_gpu0_fp16.engine
INFO: [FullDims Engine Info]: layers num: 3
0   INPUT  kFLOAT input_1:0       288x384x3       min: 1x288x384x3     opt: 32x288x384x3    Max: 32x288x384x3    
1   OUTPUT kFLOAT heatmap_out/BiasAdd:0 36x48x19        min: 0               opt: 0               Max: 0               
2   OUTPUT kFLOAT conv2d_transpose_1/BiasAdd:0 144x192x38      min: 0               opt: 0               Max: 0               

0:00:05.730978602  8978 0xaaaad8d91060 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2003> [UID = 1]: Use deserialized engine model: /home/nvidia/deepstream_tao_apps/models/bodypose2d/model.etlt_b32_gpu0_fp16.engine
0:00:06.158368285  8978 0xaaaad8d91060 INFO                 nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary-infer-engine1> [UID 1]: Load new model:/home/nvidia/deepstream_tao_apps/configs/bodypose2d_tao/bodypose2d_pgie_config.yml sucessfully
Decodebin child added: source
Decodebin child added: decodebin0
Decodebin child added: source
Decodebin child added: decodebin1
Running...
Decodebin child added: qtdemux0
Decodebin child added: qtdemux1
Decodebin child added: multiqueue0
Decodebin child added: multiqueue1
Decodebin child added: h264parse1
Decodebin child added: h264parse0
Decodebin child added: capsfilter0
Decodebin child added: capsfilter1
Decodebin child added: aacparse0
Decodebin child added: aacparse1
Decodebin child added: avdec_aac0
Decodebin child added: avdec_aac1
Decodebin child added: nvv4l2decoder0
Decodebin child added: nvv4l2decoder1
Opening in BLOCKING MODE 
Opening in BLOCKING MODE 
NvMMLiteOpen : Block : BlockType = 261 
NvMMLiteOpen : Block : BlockType = 261 
NVMEDIA: Reading vendor.tegra.display-size : status: 6 
NVMEDIA: Reading vendor.tegra.display-size : status: 6 
NvMMLiteBlockCreate : Block : BlockType = 261 
NvMMLiteBlockCreate : Block : BlockType = 261 
In cb_newpad
In cb_newpad
###Decodebin pick nvidia decoder plugin.
In cb_newpad
###Decodebin pick nvidia decoder plugin.
In cb_newpad
NvMMLiteOpen : Block : BlockType = 4 
===== NVMEDIA: NVENC =====
NvMMLiteBlockCreate : Block : BlockType = 4 
Frame Number = 0 Person Count = 4
Frame Number = 1 Person Count = 4
H264: Profile = 66, Level = 0 
NVMEDIA: Need to set EMC bandwidth : 376000 
NVMEDIA_ENC: bBlitMode is set to TRUE 
Frame Number = 2 Person Count = 4
Frame Number = 3 Person Count = 4
Frame Number = 4 Person Count = 10
Frame Number = 5 Person Count = 4
Frame Number = 6 Person Count = 4
Frame Number = 7 Person Count = 4
Frame Number = 8 Person Count = 4
Frame Number = 9 Person Count = 4
Frame Number = 10 Person Count = 4
Frame Number = 11 Person Count = 4
Frame Number = 12 Person Count = 4
Frame Number = 13 Person Count = 4
Frame Number = 14 Person Count = 4
Frame Number = 15 Person Count = 4
Frame Number = 16 Person Count = 4
Frame Number = 17 Person Count = 4
Frame Number = 18 Person Count = 4
Frame Number = 19 Person Count = 4
Frame Number = 20 Person Count = 6
Frame Number = 21 Person Count = 4
Frame Number = 22 Person Count = 4
Frame Number = 23 Person Count = 4
Frame Number = 24 Person Count = 6
Frame Number = 25 Person Count = 4
Frame Number = 26 Person Count = 6
Frame Number = 27 Person Count = 6
Frame Number = 28 Person Count = 6
Frame Number = 29 Person Count = 6
Frame Number = 30 Person Count = 4
Frame Number = 31 Person Count = 4
Frame Number = 32 Person Count = 4
Frame Number = 33 Person Count = 6
Frame Number = 34 Person Count = 6
Frame Number = 35 Person Count = 8
Frame Number = 36 Person Count = 8
Frame Number = 37 Person Count = 8
Frame Number = 38 Person Count = 8
Frame Number = 39 Person Count = 10

$ export DISPLAY=:0

HI,

root@ubuntu:/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app# export DISPLAY=:0
root@ubuntu:/home/nvidia/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app# ./deepstream-bodypose2d-app bodypose2d_app_config.yml 
Invalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keynvbufsurftransform: Could not get EGL display connection
Request sink_0 pad from streammux
Request sink_1 pad from streammux
!! [WARNING] Unknown param found : type
!! [WARNING] Unknown param found : enc
!! [WARNING] Unknown param found : udpport
!! [WARNING] Unknown param found : rtspport
!! [WARNING] Unknown param found : filename
total 1 item
group model-config found 0
Now playing: SUDO_GID=1000
Invalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keynvbuf_utils: Could not get EGL display connection
Invalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keynvbuf_utils: Could not get EGL display connection
Opening in BLOCKING MODE 
WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
0:00:02.672909701  9074 0xaaaacb7d8a70 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/home/nvidia/deepstream_tao_apps/models/bodypose2d/model.etlt_b32_gpu0_fp16.engine
INFO: [FullDims Engine Info]: layers num: 3
0   INPUT  kFLOAT input_1:0       288x384x3       min: 1x288x384x3     opt: 32x288x384x3    Max: 32x288x384x3    
1   OUTPUT kFLOAT heatmap_out/BiasAdd:0 36x48x19        min: 0               opt: 0               Max: 0               
2   OUTPUT kFLOAT conv2d_transpose_1/BiasAdd:0 144x192x38      min: 0               opt: 0               Max: 0               

0:00:02.827745749  9074 0xaaaacb7d8a70 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2003> [UID = 1]: Use deserialized engine model: /home/nvidia/deepstream_tao_apps/models/bodypose2d/model.etlt_b32_gpu0_fp16.engine
Invalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keyInvalid MIT-MAGIC-COOKIE-1 keynvbufsurface: Could not get EGL display connection
nvbufsurface: Can't get EGL display
0:00:03.034461110  9074 0xaaaacb7d8a70 WARN                 nvinfer gstnvinfer.cpp:943:gst_nvinfer_start:<primary-infer-engine1> error: Failed to set buffer pool to active
Running...
ERROR from element primary-infer-engine1: Failed to set buffer pool to active
Error details: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(943): gst_nvinfer_start (): /GstPipeline:pipeline/GstNvInfer:primary-infer-engine1
Returned, stopping playback
Average fps 0.000233
Totally 0 persons are inferred
Deleting pipeline

Hi,

Or do I need to modify the yml file? If yes, how?

output:
  ## 1:file ouput  2:fake output 3:eglsink output 4:RTSP output
  type: 1
  ## 0: H264 encoder  1:H265 encoder
  enc: 0
  bitrate: 2000000
  udpport: 2345
  rtspport: 8554
  ##The file name without suffix
  filename: test

Actually you already run successfully.
Use "$ ls -rlt " to check the result file.