Orange Pi 5 (and variants) Object Detection

How it works

PhotonVision runs object detection on the Orange Pi 5 by use of the RKNN model architecture, and this JNI code.

Supported models

PhotonVision currently ONLY supports 640x640 Ultralytics YOLOv5, YOLOv8, and YOLOv11 models trained and converted to .rknn format for RK3588 SOCs! Other models require different post-processing code and will NOT work.

Converting Custom Models

Warning

Only quantized models are supported, so take care when exporting to select the option for quantization.

PhotonVision now ships with a Python Notebook that you can use in Google Colab or in a local environment. In Google Colab, you can simply paste the PhotonVision GitHub URL into the “GitHub” tab and select the rknn_conversion.ipynb notebook without needing to manually download anything.

Please ensure that the model you are attempting to convert is among the supported models and using the PyTorch format.