Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) AGX Xavier
• DeepStream Version 6.0
• JetPack Version (valid for Jetson only) 4.6
• TensorRT Version (jetpack 4.6 default)
• NVIDIA GPU Driver Version (valid for GPU only) (jetpack 4.6 default)
• Issue Type( questions, new requirements, bugs) why do I get internal data stream error when running examples on 264 streams?
I’m able to run the sample scripts eg /samples/configs/deepstream-app:
deepstreamp-app -c source12_12080p_dec…txt works fine.
But when I try to run python_apps or compile deepsteram test-1 app, it fails.
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
Running a docker container:
IMAGE=nvcr.io/nvidia/deepstream-l4t:6.0-samples
xhost +
IMAGE=nvcr.io/nvidia/deepstream-l4t:6.0-samples
docker run -it --net=host --runtime nvidia
-w /opt/nvidia/deepstream/deepstream-6.0
-v /tmp/.X11-unix/:/tmp/.X11-unix
-v /usr/src/:/opt/nvidia/deepstream/deepstream-6.0/repos
–mount type=bind,source=/var/output,target=/var/output
$IMAGE
/bin/bash
when the docker is running then install the following packages:
$ apt-get install libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev -y
Then the deepstream-script apps works eg.
cd /opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app
deepstream-app -c source12_1080p_dec_infer-resnet_tracker_tiled_display_fp16_tx2.txt
WORKS!!
(the script is using the following stream: …/…/streams/sample_1080p_h264.mp4 as source)
But…
$ cd /opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream-test1#
$ make CUDA_VER=10.2
$ ./deepstream-test1-app …/…/…/…/samples/streams/sample_1080p_h264.mp4
generates the error:
0:00:03.809349028 722 0x55ab9a84f0 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2004> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
0:00:03.817216372 722 0x55ab9a84f0 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus: [UID 1]: Load new model:dstest1_pgie_config.txt sucessfully
Running…
ERROR from element h264-parser: Internal data stream error.
Error details: gstbaseparse.c(3611): gst_base_parse_loop (): /GstPipeline:dstest1-pipeline/GstH264Parse:h264-parser:
streaming stopped, reason not-negotiated (-4)
Returned, stopping playback
Deleting pipeline
I get the same error when installing the python bindings and trying to run test1 app.
I’ve tried to run it on the *.mjpeg stream instead but then everything hangs.
why is this happening?
best regards/
Daniel Grafström
but
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)