Detection problem with Mobile Net on video from host

krishnashravan Please provide minimal repro example.

erik
Hi erik i have attached the files here
the test 4 file gives a error where the video keeps on changing the size of the preview

the test 5 file gives a error where the video shifts to live inferencing in between the frames
the common error that i found was that both these stop working after 30 seconds
only live inferencing works fine but the video inferencing stops after 30 seconds
let me know if u need anything else

This isn't reproducible.

 python .\test4.py
Traceback (most recent call last):
  File "D:\Downloads\yolov8-testing-pt-files-New%20folder\test4.py", line 175, in <module>
    parser = argparse.ArgumentParser()
NameError: name 'argparse' is not defined

erik
i have made the changes and use the yolov8n.json file for the metadata
here

Again, this is not reproducible. Did you even try running the test4.py/test5.py?

erik

sorry erik
but i fixed it

@erik

Hi, can you please provide the code to run the inference on a video file using yolov5?

@Unknown perhaps look at
https://docs-old.luxonis.com/projects/sdk/en/latest/features/replaying/
SDK also has good support for YOLO models.

Thankyou @erik

There are modules for object Tracking using mobilenet ssd but it did not work well for yolov5.
can you please give module for object tracker using yolov5.

@erik

Whether we can run dlib tracker on-device together with yolov5 object detection?

@erik okay sure, Thank you.
Can you please let me know about the query given below.
Whether we can run dlib tracker on-device together with yolov5 object detection?

Unknown
Depthai has proprietary tracking algorithms that can run on RVC. Addding custom tracking (on-device) is not possible on RVC2.
You would have to port the tracking to host side. The rest of the pipeline (yolo and others) should still be run on device.

Thanks,
Jaka

Thankyou @jakaskerl