markusbr

Do you have a chance to start in a new, clean environment? Do you already have gstreamer and plugins installed with a version number scheme newer/same than the downloaded files?...

(trying Docker is just an idea to install in a well-defined, "clean" environment removing your individual environment from the equation, no recommendation for dockerization)

DL-Streamer defined Ubuntu 22 as the "supported version" (see https://dlstreamer.github.io/get_started/install/install_guide_ubuntu.html). Your first installations 3 years ago - you might have installed OpenVINO first and then DL-Streamer? (old versions even came...

The latest version (the last published release) has announced: > Deprecation Notices > Ubuntu 20.04 is no longer actively supported. > See see full list of currently deprecated properties in...

hmm, can'T find the older installation notes either... the DL-Streamer GitHub repo once contained a Wiki section - which has no version control either... A good summary I found always...

Can you maybe show a sample/screenshot? Your model, your input-material, your (re-)trained models might require different tuning for NMS-, IOU-, confidence-level. The script `detect.py` (see e.g. https://github.com/ultralytics/yolov5/blob/master/detect.py#L61) sets default values...

Do you setup your pipeline programmatically (C/C++, Python, Rust, etc.), how? Can you share your/a piece of code for the dev-team to reproduce and analyze? Do you have a chance...

How do you start the Docker container? Can you try temporarily running with root user like `docker run -it -u 0 --rm ...` and install packages? Or creating your own...

@navyverma which container are you talking about, a pre-built OpenVino-DLStreamer container or your own container (using your own Dockerfile, but based on a DL-Streamer image)? Can you start the container...

Do you mean something like this? - "https://docs.openvino.ai/2021.4/ovms_extras_openvino-operator-openshift-readme.html" - "https://developers.redhat.com/learning/learn:openshift-data-science:get-started-intel-openvino/resource/resources:start-your-jupyter-notebook-server-intel-openvino" - "https://developers.redhat.com/learn/openshift-data-science/get-started-intel-openvino" - "https://www.intel.com/content/www/us/en/developer/articles/technical/red-hat-openshift-data-science-with-intel-ai-tools.html"