Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
Xavier NX
• DeepStream Version
Whatever installs with JetPack 5.0.2
• JetPack Version (valid for Jetson only)
5.0.2
• TensorRT Version
Whatever installs with JetPack 5.0.2
• NVIDIA GPU Driver Version (valid for GPU only)
Whatever installs with JetPack 5.0.2
• Issue Type( questions, new requirements, bugs)
I’ve built (on the Xavier) and installed the Deepstream python bindings from this repo:
I’ve installed them inside this Docker container:
nvcr.io/nvidia/deepstream-l4t:6.1.1-samples
Steps performed inside the container:
- apt-get update
- apt install -y git python-dev python3 python3-pip python3.8-dev cmake g++ build-essential libglib2.0-dev libglib2.0-dev-bin python-gi-dev libtool m4 autoconf automake
- apt install libcairo2-dev pkg-config python3-dev
- rm /usr/bin/pip3
- apt reinstall python3-pip
- pip3 install --upgrade pip
- pip install pycairo
- cd /opt/nvidia/deepstream/deepstream/sources/apps/
- git clone GitHub - NVIDIA-AI-IOT/deepstream_python_apps: DeepStream SDK Python bindings and sample applications
- cd deepstream_python_apps/
- git submodule update --init
- apt-get install --reinstall ca-certificates
- apt install python3-gi python3-dev python3-gst-1.0 python-gi-dev git python-dev python3 python3-pip python3.8-dev cmake g++ build-essential libglib2.0-dev libglib2.0-dev-bin libgstreamer1.0-dev libtool m4 autoconf automake libgirepository1.0-dev libcairo2-dev
- cd 3rdparty/gst-python/
- ./autogen.sh
- Make && make install
- cd /opt/nvidia/deepstream/deepstream/sources/apps/deepstream_python_apps/bindings
- Mkdir build
- Cd build
- cp /home_nvidia/Downloads/pyds-1.1.4-py3-none-linux_aarch64.whl .
- pip3 install pyds-1.1.4-py3-none-linux_aarch64.whl
- cd /opt/nvidia/deepstream/deepstream/sources/apps/deepstream_python_apps/
- mv apps/* ./
- cd deepstream-test1/
- python3 deepstream_test_1.py …/…/…/…/samples/streams/sample_qHD.h264
I’m trying to run deepstream_test_1.py, but get this error:
Creating Pipeline
Creating Source
Creating H264Parser
Creating Decoder
Creating EGLSink
Playing file /deepstream-6.1/samples/streams/sample_720p.h264
Adding elements to Pipeline
Linking elements in the Pipeline
Starting pipeline
Using winsys: x11
Opening in BLOCKING MODE
0:00:00.639513086 91 0x1a57fe30 WARN nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1170> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5
0:00:05.971814988 91 0x1a57fe30 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
INFO: [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40
0:00:06.049104417 91 0x1a57fe30 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: Use deserialized engine model: /deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
0:00:06.062082097 91 0x1a57fe30 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:dstest1_pgie_config.txt sucessfully
NvMMLiteOpen : Block : BlockType = 261
NVMEDIA: Reading vendor.tegra.display-size : status: 6
NvMMLiteBlockCreate : Block : BlockType = 261
Frame Number=0 Number of Objects=10 Vehicle_count=6 Person_count=4
0:00:06.367161534 91 0x1a118ea0 WARN nvinfer gstnvinfer.cpp:2300:gst_nvinfer_output_loop: error: Internal data stream error.
0:00:06.367267741 91 0x1a118ea0 WARN nvinfer gstnvinfer.cpp:2300:gst_nvinfer_output_loop: error: streaming stopped, reason error (-5)
Error: gst-stream-error-quark: Internal data stream error. (1): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(2300): gst_nvinfer_output_loop (): /GstPipeline:pipeline0/GstNvInfer:primary-inference:
streaming stopped, reason error (-5)
I get the same error when I try to run some of the other test applications.
After some reading, I see I should try a basic Gstreamer command to see if that works. So I’ve run the following command both directly on the Xavier and also inside the Docker container on the Xavier:
gst-launch-1.0 videotestsrc ! nvvidconv ! nvegltransform ! nveglglessink
The command shows the test pattern video when run directly from the Xavier, but when running from inside the container I get this error (which is similar to the above error):
Setting pipeline to PAUSED …
Using winsys: x11
Pipeline is PREROLLING …
Got context from element ‘eglglessink0’: gst.egl.EGLDisplay=context, display=(GstEGLDisplay)NULL;
ERROR: from element /GstPipeline:pipeline0/GstVideoTestSrc:videotestsrc0: Internal data stream error.
Additional debug info:
gstbasesrc.c(3072): gst_base_src_loop (): /GstPipeline:pipeline0/GstVideoTestSrc:videotestsrc0:
streaming stopped, reason error (-5)
ERROR: pipeline doesn’t want to preroll.
Setting pipeline to NULL …
Freeing pipeline …
I’m not sure if it’s relevant, but I used this command to start the docker container on the Xavier:
docker run -ti --runtime nvidia --gpus all --network host -v /tmp/.X11-unix:/tmp/.X11-unix -v /home/nvidia/:/home_nvidia -p 127.0.0.1:8888:8888 --device /dev/video0 nvcr.io/nvidia/deepstream-l4t:6.1.1-samples
I’ve done a decent bit of searching but am not finding any obvious issues.
Any help would be appreciated, thanks.