Digital2Slave
Digital2Slave
@Deep55033 嗯，我这边是只测试了OpenCV 4.6.0版本。
> > Same question, I already try onn2ncnn and pnnx but none works sob > > my model converted from onnx. you should change the split to slice in c2f...
> > > > Same question, I already try onn2ncnn and pnnx but none works sob > > > > > > > > > my model converted from onnx....
@apanand14 Not focus on yolov8 yet.
@apanand14 I think you should use [export_seg.py](https://github.com/triple-Mu/YOLOv8-TensorRT/blob/main/export_seg.py) to convert `yolov8s-seg.pt` to `yolov8s-seg.onnx`. But here is an issue `ArgMax not supported yet!` when use `onnx2ncnn`. There maybe two ways to handle...
> i have update the readme show how to change v8 code Refer the codes [convert to onnx for ncnn](https://github.com/FeiGeChuanShu/ncnn-android-yolov8) in README. I modified `ultralytics/ultralytics/nn/modules.py` the `forward` method in `C2f`...
> @Digital2Slave i have fixed the readme for seg model. you can try it. @FeiGeChuanShu Thanks a lot! Great job! As for yolov8 segment model. I need modify three `forward`...
https://github.com/Digital2Slave/ncnn-android-yolov8-seg/wiki/Convert-yolov8%E2%80%90seg-to-ncnn-model-step-by-step
https://github.com/Digital2Slave/ncnn-android-yolov8-seg/wiki/Convert-yolov8%E2%80%90seg-to-ncnn-model-step-by-step
> up! https://github.com/nihui/ncnn-android-yolov8