KSNN Segmentation Fault (Except YOLOv3)

Which Khadas SBC do you use?

VIM3 Pro

Which system do you use? Android, Ubuntu, OOWOW or others?

Ubuntu 20.04

Which version of system do you use? Khadas official images, self built images, or others?


I’m working on Darknet in the example codes in Ksnn (ksnn/examples/darknet at master · khadas/ksnn · GitHub) (I got wrong outputs when I did ONNX conversion. That’s why I’m trying Darknet.). While the yolov3 models I trained myself are working without any errors, I get a “Segmantation Fault” error when inference is given to the yolov3-tiny and yolov4-tiny models (after conversion). What is the cause of this problem? Is KSNN Inference only suitable for yolov3?