Unknown

Hi @Unknown,

Interesting. I'll look into it and let you know when I discover something.

Best,
Jan

Hi @Unknown ,
You can do frame skipping, but FPS would be the same - or do you mean to buffer eg. 30 frames at a time (from 1 sec), and then process those for the next ₅ seconds? You could do that as well using Scirpt node, some relevant example here:
https://docs.luxonis.com/software/depthai/examples/script_change_pipeline_flow/

Hi @Unknown , we don't have comparisons for yolov5s directly with these sizes, but we do have for yolov6, and it's similar - 640x640 is about 2x slower than 416x416:

From here:
https://docs.luxonis.com/hardware/platform/rvc/rvc2/

So yes, I'd say it's normal. Perhaps go with smaller model, or with smaller architecture (nano instead of small).

@Unknown it's exactly the same, you can link YoloDetectionNetwork the same way you link MobileNetDetectionNetwork to the ObjectTracker node.

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