markusbr
markusbr
FP32 versus FP16 - not BFLOAT16 ;-)
A model in FP16 can be used with the OpenVINO CPU-plugin as well as with other plugins/for other devices (like a VisionProcessingUnit VPU). Wanting to use FP16 over FP32 can...
Besides CPU, GPU, NPU, (VPU, FPGA), AUTO and MULTI, have you tried to experiment with HETERO (see "https://docs.openvino.ai/2024/openvino-workflow/running-inference/inference-devices-and-modes/hetero-execution.html")?
Can you provide more details about your environment (HW, SW, OS, Python version, with/without Python-VirtualEnvironment), please? Which Jupyter notebook are you referring to? Which model do you use, is it...
Can you provide more details about your environment, please? Do you refer to this Jupyter-Notebook https://github.com/openvinotoolkit/openvino_notebooks/blob/latest/notebooks/sana-image-generation/sana-image-generation.ipynb ? Which HW are you using, what about of system memory do you have?...
When using the model variant "Efficient-Large-Model/Sana_Sprint_0.6B_1024px_diffusers" (default, the first model in the drop-down menu), keeping the checkbox for weight-compression selected, using MS-Win-11-Pro on an Intel Core Ultra 7 155H laptop,...
Directly under "https://github.com/bes-dev/stable_diffusion.openvino" (using a browser) there you can find `demo.py`:  The demo is part of this repo, not part of OpenVINO. You might try to install this repo...
It sounds like you haven't cloned this GIT repo, yet. First, you need to clone the repo, e.g. via "git clone https://github.com/bes-dev/stable_diffusion.openvino.git" - then you will get all the files...
You can find the sources here in this repo where you created your issue. The base of this repo is: "https://github.com/spmallick/learnopencv/" The code for the referenced blog can be found...
Have you checked "https://dlstreamer.github.io/dev_guide/python_bindings.html#gvapython-element" with a link to an example: > Please see samples for gvapython element in [this folder](https://github.com/dlstreamer/dlstreamer/tree/master/samples/gstreamer/gst_launch/gvapython/face_detection_and_classification)