Q-engineering
Q-engineering
@mxochicale, Feel free to fork the repo for add-ons, and extensions. I do not have the time to manage such a project, busy as I am with other (commercial) projects....
@lecifire, I'm sorry. C++ is my native tongue. I'm not familiar with Python.
@Rawpower9, Can it be: [#4619](https://github.com/Tencent/ncnn/issues/4619#issuecomment-1546820786)? nihui has solved it last sunday. You have to re-install ncnn on your Raspberry Pi.
@pastukhov-aleksandr, Porting from .pt to ncnn can be a nightmare. In your case ncnn can't find a proper output layer. It suggests you use the layer "output0". I hope it...
Got them! (Remember, no promises.)
@yrik, I'm sorry. At the moment I'm busy with a lot of projects. To be honest, it is hard to find time to investigate the issue. Knowing FeiGeChuanShu, you're in...
That's the news we all waiting for.
Did you see this page? https://docs.ultralytics.com/integrations/ncnn/#deploying-exported-yolov8-ncnn-models
I've used the models from @FeiGeChuanShu see: https://github.com/FeiGeChuanShu/ncnn-android-yolov8
It is possible. You will hit 0.8-1.2 FPS (more or less the same as with YoloV5) BTW, the code means to be adapted for the segmentation.