markusbr

Does "compiling with clang-18 or 17" mean you are compiling with "C++23"? (found e.g. this "https://stackoverflow.com/questions/71828288/why-is-stdaligned-storage-to-be-deprecated-in-c23-and-what-to-use-instead")

Using the default-algorithm for INT8 quantization (instead of using the "accuracy-aware" algorithm) can come with a slightly reduced accuracy... The sample "object_detection_demo.py" has a default-value `'-t', '--prob_threshold', default=0.5`, which you...

Can you provide more details about the problem you are seeing, please? After INT8-quantization no objects were detected at all anymore, compared to the "original models" (F16, FP32)?

I saw the same - this is an issue to `strtod()` - there are lots of discussions about flouting-point numbers and their exact representation; "0" seems such a "difficult" case....

@JoeLoginIsAlreadyTaken have you found a solution? Did it help to comment-out the section as mentioned above?

How have you set-up your environment, which versions do you use? How have you build the application? Have you built OpenCV from source? Can you find the mentioned library `opencv_core_parallel_openmp`...

Can you descrfibe how you have set up your environment? The README doesn't mention much dependencies, other than Meson and OpenCV (without details about versions and configuration, as e.g. OpenCV...

Are you sure your notebook uses `inline` so that rendering and displaying happens within the notebook's context? The mentioned repo seems to be a standalone application running in a shell...

Are you referring to one of the samples here under "https://github.com/spmallick/learnopencv" or referring to one of the OpenCV APIs? There are several repositories around the ORB-SLAM3 paper, with/without IMUs, with/without...

Me personally no experience on ORB-SLAM, sorry. There are a lot of repositories and for instance examples using Matlab. If you could provide more details about the exercise, the prerequisites...