Can't work deepstream app with Jetson Orin AGX in sink phase

• Hardware Platform (Jetson / GPU) Jetson AGX Orin 64GB
**• DeepStream Version 6.3 **
• JetPack Version (valid for Jetson only) 5.1.2 L4T 35.4.1
**• TensorRT Version : 8.5.2 **
• NVIDIA GPU Driver Version (valid for GPU only) : CUDA 11.4
• Issue Type( questions, new requirements, bugs) question

I’m using nvidia docker container from this docker File

FROM nvcr.io/nvidia/deepstream:6.3-triton-multiarch
WORKDIR /app

RUN apt-get update
RUN apt-get install -y --no-install-recommends curl v4l-utils
RUN apt-get update && apt-get install -y \
    libegl1 \
    libgl1-mesa-glx \
    libgl1-mesa-dri \
    libx11-6 \
    libxext6 \
    x11-apps

RUN apt install -y \
    libssl1.1 \
    libgstreamer1.0-0 \
    gstreamer1.0-tools \
    gstreamer1.0-plugins-good \
    gstreamer1.0-plugins-bad \
    gstreamer1.0-plugins-ugly \
    gstreamer1.0-libav \
    libgstreamer-plugins-base1.0-dev \
    libgstrtspserver-1.0-0 \
    libjansson4 \
    libyaml-cpp-dev

ENV NVIDIA_DRIVER_CAPABILITIES $NVIDIA_DRIVER_CAPABILITIES,video


RUN rm -rf /var/lib/apt/lists/*
RUN /opt/nvidia/deepstream/deepstream/user_additional_install.sh

RUN  cd /opt/nvidia/deepstream/deepstream-6.3/ \
    && git clone https://github.com/NVIDIA-AI-IOT/deepstream_tao_apps.git \
    && git clone https://github.com/marcoslucianops/DeepStream-Yolo.git \
    && git clone https://github.com/ultralytics/ultralytics

ENV CUDA_VER=11.4
RUN cd /opt/nvidia/deepstream/deepstream-6.3/DeepStream-Yolo \
    && make -C nvdsinfer_custom_impl_Yolo clean && make -C nvdsinfer_custom_impl_Yolo

    


ENV RYE_HOME="/opt/rye"
ENV PATH="$RYE_HOME/shims:$PATH"

RUN curl -sSLf https://rye.astral.sh/get | RYE_INSTALL_OPTION="--yes" bash
COPY pyproject.toml README.md /app/

RUN rye sync

The docker build is going well but when I start docker and run deepstream-app cmd I get this error

** ERROR: <create_encode_file_bin:506>: create_encode_file_bin failed
** ERROR: <create_sink_bin:831>: create_sink_bin failed
** ERROR: <create_processing_instance:956>: create_processing_instance failed
** ERROR: <create_pipeline:1576>: create_pipeline failed
** ERROR: <main:697>: Failed to create pipeline
Quitting
nvstreammux: Successfully handled EOS for source_id=0

The deepsteam config is this

[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5

[tiled-display]
enable=1
rows=1
columns=1
width=1280
height=720
gpu-id=0
nvbuf-memory-type=0

[source0]
enable=1
type=3
#device=/dev/video0
uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4
num-sources=1
gpu-id=0
cudadec-memtype=0

[sink0]
enable=1
type=3
#container=1
#bitrate=4000000
#rtsp-port=8554
#udp-port=5400
output-file=./result.mp4
sync=0
gpu-id=0
nvbuf-memory-type=0

[osd]
enable=1
gpu-id=0
border-width=5
text-size=15
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Serif
show-clock=0
clock-x-offset=800
clock-y-offset=820
clock-text-size=12
clock-color=1;0;0;0
nvbuf-memory-type=0

[streammux]
gpu-id=0
live-source=1
batch-size=1
batched-push-timeout=1
width=1920
height=1080
enable-padding=0
nvbuf-memory-type=0

[primary-gie]
enable=1
gpu-id=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=config_infer_primary_yoloV8.txt

[tests]
file-loop=0

#[tracker]
#enable=0
#tracker-width=640
#tracker-height=384
#ll-lib-file=/opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
#ll-config-file=config_tracker_NvDCF_perf.yml
#gpu-id=0
#enable-batch-process=1

It seems sink error but I can’t fine any solution.
Could someone help me?

First, make sure deepstream-app can run correctly in nvcr.io/nvidia/deepstream:6.3-triton-multiarch. If you start it directly with the following command line, can it work properly?

docker run -it --rm --network=host --runtime nvidia  -e DISPLAY=$DISPLAY -w /opt/nvidia/deepstream/deepstream-6.3  -v /tmp/.X11-unix/:/tmp/.X11-unix nvcr.io/nvidia/deepstream:6.3-triton-multiarch

it doesn’t work with same error.

Please configure the correct parameters. Additionally, please ensure that the configurations in the SDK can run correctly first, such as

 deepstream-app -c /opt/nvidia/deepstream/deepstream/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
[sink1]
enable=1
type=3
#1=mp4 2=mkv
container=1
#1=h264 2=h265
codec=1
#encoder type 0=Hardware 1=Software
enc-type=0
sync=0
#iframeinterval=10
bitrate=2000000
#H264 Profile - 0=Baseline 2=Main 4=High
#H265 Profile - 0=Main 1=Main10
# set profile only for hw encoder, sw encoder selects profile based on sw-preset
profile=0
output-file=out.mp4
source-id=0

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.