markusbr

The Jupyter notebook you are referring to "https://github.com/openvinotoolkit/openvino_notebooks/blob/latest/notebooks/llm-agent-react/llm-agent-react.ipynb" has NPU explicitely excluded, see cell number 4: > from notebook_utils import device_widget > llm_device = device_widget("CPU", exclude=["NPU"]) > llm_device Are you...

Can you maybe provide a few pictures about what you want to achieve (in comparison what you currently get)? Can you describe your use-case with more details? Do you want...

I'm sorry, but I don't have experience with the gvapython plugin itself. Maybe the following gives additional insights: https://github.com/dlstreamer/dlstreamer/issues/148 https://github.com/dlstreamer/dlstreamer/blob/master/samples/gstreamer/python/draw_face_attributes/draw_face_attributes.py https://github.com/dlstreamer/dlstreamer/blob/master/samples/gstreamer/python/draw_face_attributes/draw_face_attributes.sh https://dlstreamer.github.io/api_ref/class_GVA_VideoFrame.html https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/Image-manipulation-for-DLStreamer-pipeline/m-p/1272894/highlight/true EDIT: Using something like this: https://learnopencv.com/face-morph-using-opencv-cpp-python/ https://github.com/spmallick/learnopencv/tree/master/FaceMorph...

Can you share your pipeline (again), please? Do you use multiple attached regions, need to detect multiple, different object classes (like one ROI covering the road counting cars and a...

In your C++ environment you very likely have a (very) different version of OpenCV installed than in your Python environment. Depending on your camera stream you might need or not...

This code to grab and capture a frame from the camera and displaying it looks good. There is a lot happening in the background automatically (grabbing and capturing and decoding...

Can you use the Ubuntu22 variant instead of the Ubuntu24 variant (same version of DL-Streamer and OpenVINO), for the time being, temporarily? (I see similar posts "in the Internet", maybe...

Have a look under "https://dlstreamer.github.io/dev_guide/python_bindings.html", specifically under the section "https://dlstreamer.github.io/dev_guide/python_bindings.html#performance-considerations". Culd you try to build the pipeline in Python (instead of command-line and `gst-launch-1.0` executable) and use callbacks (like in...

From orignally `~58.7 fps` to `~46 fps` seems to be related to the "chain" from a console executable to DL-Streamer plugin to passing to a Python interpreter to running the...

You could even move your processing to a C/C++ library (and using e.g. OpenCL to delegate the code to GPU) and call that from within your implementation. Are you sure...