Open neocoretechs opened 1 year ago
I am currently struggling with this issue as well. @neocoretechs did you find a work around? I was hoping it was just setting the right opset but it looks like the .onnx in this repository was not made with that export (or maybe an older version). I'm using YOLOv5 🚀 v7.0-145-g94714fe Python-3.8.10 torch-1.10.1+cu111 Ubuntu 20.04 and onnx 1.9.0.
Update: Khadas forked the ultralytics/yolov5 repo and that script worked. https://github.com/rockchip-linux/rknpu2/issues/57
Using the yolov5s.onnx supplied in the toolkit demo conversion results in a working rknn model, but using default export.py from ultralytics results in the one layer model that selects all possible bounding boxes.